{ "data": { "a": { "slug": "clawpost", "name": "Clawpost", "vendor": "Frank Harris", "vendorUrl": "https://github.com/hirefrank/clawpost", "kind": "mcp", "category": "agent-inboxes", "summary": "Clawpost is an open-source Cloudflare Worker you deploy yourself to give an AI agent its own email address, with an MCP server, a REST API and a CLI for sending, receiving, searching, drafts and sender approval.", "url": "https://www.anchorterminal.com/tools/clawpost", "markdownUrl": "https://www.anchorterminal.com/tools/clawpost.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/clawpost.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/clawpost.json", "dns": "clawpost.grade.anchorterminal.com", "repo": "https://github.com/hirefrank/clawpost", "license": "MIT", "transports": [ "streamable-http", "http" ], "packages": [], "auth": "api-key", "authNotes": "One shared secret, `CLAWPOST_API_KEY`, set as a Worker secret and sent as `Authorization: Bearer` to both the REST API and the MCP endpoint, compared in constant time. No scopes, users or per-client keys. Inbox and alias management also needs a Cloudflare API token on the Worker.", "pricing": "free", "pricingNotes": "Free, MIT-licensed software. Running it needs the Cloudflare Workers Paid plan ($5 a month) for Durable Objects and outbound Email Service; the README puts a typical agent at about $5 a month. Resend can be used for outbound instead.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the source or README (checked 2026-11-06).", "endpoints": [] }, "toolCount": 21, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://github.com/hirefrank/clawpost#readme", "capabilities": [ "email.inbox", "email.send", "email.inbound", "email.threads", "email.domains" ], "tags": [ "self-hosted", "open-source", "mcp", "remote-mcp", "api-key", "cloudflare", "webhooks", "approvals", "typescript", "cli", "pre-1.0" ], "lastRelease": "2026-04-01", "graded": true, "anchor": { "graded": true, "score": 36.8, "grade": "F", "agentReady": false, "rank": 1383, "ranked": true, "rankOf": 1510, "categoryRank": 12, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 53, "maintenance": 2, "payments": 60, "reliability": 8, "schema": 54, "security": 42, "transparency": 32 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-06" }, "negative": 0, "verdict": "A small self-hosted agent inbox whose sender-approval gate keeps unknown senders' mail away from the agent by default, with drafts for human review. It is one developer's project, unchanged since 1 April 2026, with one all-powerful key, no releases, tests or CI.", "bestFor": "A developer who wants an agent inbox on their own domain and Cloudflare account with a default approval gate.", "strengths": [ "Mail from unapproved senders is stored but hidden from every query tool until a sender is approved", "Drafts let a person review mail before an agent's message goes out", "Self-hosted on the deployer's own Cloudflare account, so mail stays in their D1 and R2", "21 MCP tools with typed zod inputs, plus a REST API and a CLI with `--json` output", "Free software; running costs are the Cloudflare Workers Paid plan at $5 a month" ], "weaknesses": [ "One shared API key grants every REST and MCP operation; no scopes or read-only key", "No commits since 1 April 2026, no tags or releases, no CI and no tests", "No idempotency on sends and no MCP tool annotations", "Tool descriptions are one line, such as `Send an email`, with no when-not-to-use guidance", "README says MIT but no LICENSE file is in the repository" ], "agentNotes": [ "Expect unknown senders' mail to be invisible until `approve_sender` runs; check `list_pending` for metadata first", "Use `create_draft` instead of `send_email` when a person should review the message", "Send to one address per call or comma-separate recipients in `to`; a retried send isn't deduplicated", "Treat the deployer's Worker URL and `CLAWPOST_API_KEY` as full access to the mailbox" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "F", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 36.8 } ], "editorialScores": { "ergonomics": 53, "maintenance": 2, "payments": 60, "reliability": 8, "schema": 54, "security": 42, "transparency": 50 }, "provenanceScore": 13, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "git clone https://github.com/hirefrank/clawpost \u0026\u0026 cd clawpost \u0026\u0026 bun install \u0026\u0026 bun run db:migrate \u0026\u0026 bun run deploy", "config": { "mcpServers": { "clawpost": { "headers": { "Authorization": "Bearer YOUR_CLAWPOST_API_KEY" }, "type": "streamable-http", "url": "https://\u003cyour-worker\u003e.workers.dev/mcp" } } } }, "letme": { "capability": "https://letme.dev/email.inbox", "tool": "https://letme.dev/clawpost" }, "area": "communication", "provenance": { "legalEntity": "", "domain": "github.com", "domainRegistered": "", "endpointOnVendorDomain": false, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-11-06", "notes": [ "A personal repository under the GitHub account hirefrank; every commit but one merged pull request is by Frank Harris. No company, terms or privacy policy, as expected for self-hosted software.", "The README's licence section says MIT and SKILL.md declares MIT, but no LICENSE file is committed.", "The endpoint is whatever Worker URL the deployer chooses, usually on workers.dev.", "GitHub's API refused our requests for its rate limit on 6 November 2026, so stars and open issues weren't read; the code and history come from a shallow clone." ], "score": 13 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/clawpost.json", "live": { "slug": "clawpost", "githubStars": 6, "securityTxt": { "url": "https://github.com/.well-known/security.txt", "state": "valid", "expires": "2026-12-07T16:01:24z", "checkedAt": "2026-11-07T16:01:24.824706262Z" }, "updatedAt": "2026-11-07T16:01:24.824706262Z" } }, "answer": "mails.ai Agent Email scores 65.2 (B) on agent readiness against Clawpost's 36.8 (F), and leads in 6 of 7 scored categories. Clawpost leads on payments \u0026 pricing.", "b": { "slug": "mails-ai", "name": "mails.ai Agent Email", "vendor": "Mails.ai", "vendorUrl": "https://mails.ai", "kind": "http-api", "category": "agent-inboxes", "summary": "Hosted email API that gives each AI agent its own address to send, receive and thread mail, with a prompt-injection scan on every inbound message. Reached over REST, TypeScript and Python SDKs, and an MCP server.", "url": "https://www.anchorterminal.com/tools/mails-ai", "markdownUrl": "https://www.anchorterminal.com/tools/mails-ai.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/mails-ai.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/mails-ai.json", "dns": "mails-ai.grade.anchorterminal.com", "repo": "https://github.com/mailsai/mailsai", "license": "Proprietary hosted API under the mails.ai terms of service. The MCP server, the TypeScript SDK and the Python SDK in mailsai/mailsai are MIT", "transports": [ "http", "streamable-http", "stdio" ], "remoteUrl": "https://api.mails.ai/v1", "packages": [ { "registry": "npm", "name": "@mailsai/mcp-server" }, { "registry": "npm", "name": "@mailsai/sdk" }, { "registry": "pypi", "name": "mailsai" } ], "auth": "api-key", "authNotes": "Bearer API keys only (`mk_live_` or `mk_test_` plus 32 hex characters), with no query-string or `x-api-key` option. Each key carries any of the send, read, manage and draft scopes (draft writes drafts and never sends), can be bound to one agent with `agent_id`, which since 10 October confines it to that agent's mail, can take an `expires_at`, and is created and revoked by API or in the dashboard. Test keys run the whole API without sending mail or billing. The hosted MCP endpoint at https://api.mails.ai/mcp takes the same key as a Bearer header, or an OAuth sign-in from AI clients (https://mails.ai/docs/authentication, https://mails.ai/changelog/sign-in-from-your-ai-client-a-real-inbox-and-a-cli)", "pricing": "freemium", "pricingNotes": "Free plan with 3,000 emails and 3,000 inbound replies a month and one agent, no card, magic-link signup. Pro $20 a month for 5 agents, 50,000 emails and 50,000 inbound replies and custom domains. Scale $99 a month for unlimited agents, 250,000 emails and 500,000 inbound replies, with OpenID Connect single sign-on. Yearly billing gives two months free. A dedicated IP is on request on Scale, and Pro and Scale can send through the customer's own Amazon SES account (https://mails.ai/pricing, checked 2026-11-01).", "priceSummary": "$20 / mo", "where": "both", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, the OpenAPI spec, the pricing page or llms.txt. Billing runs through Stripe subscriptions (checked 2026-10-05).", "endpoints": [] }, "toolCount": 73, "popularity": { "githubStars": null, "npmWeekly": 650, "pypiWeekly": 116, "asOf": "2026-10-05" }, "docsUrl": "https://mails.ai/docs", "llmsTxt": "https://mails.ai/llms.txt", "openapi": "https://api.mails.ai/v1/openapi.json", "registryName": "ai.mails/agent-email", "capabilities": [ "email.inbox", "email.send", "email.inbound", "email.threads", "email.domains", "guard.injection" ], "tags": [ "hosted", "freemium", "no-card", "mcp", "llms-txt", "openapi", "typescript", "python", "webhooks", "streaming", "status-page", "closed-source" ], "lastRelease": "2026-10-16", "graded": true, "anchor": { "graded": true, "score": 65.2, "grade": "B", "agentReady": false, "rank": 434, "ranked": true, "rankOf": 1510, "categoryRank": 4, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 83, "maintenance": 80, "payments": 30, "reliability": 80, "schema": 84, "security": 78, "transparency": 65 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-01" }, "negative": -8, "negativeNotes": [ "2026-10-10. The release announced that day changed published behaviour for existing clients with no earlier notice found. Webhooks on `*` stopped receiving thread.created, thread.updated and thread.deleted, keys tied to one agent began answering 404 for other agents' mail and 403 for webhooks and labels, and 429s stopped carrying Retry-After for waits over 60 seconds. A same-day change, -3 (https://mails.ai/changelog/sign-in-from-your-ai-client-a-real-inbox-and-a-cli)", "October 2026. The October summary of 1 November lists as fixed that \"A test key can no longer change, send or delete a draft created with a live key.\" A fix of the service's own access flaw with no security advisory, -3. Agent-bound keys reaching other agents' mail until 10 October is counted in the same-day term above, since the vendor announced their confinement as a behaviour change (https://mails.ai/changelog/whats-new-in-october)", "Until 2026-10-05. The sub-processor list named Anthropic for inbound inference and left out ten services already in use, among them OpenAI, which runs the injection scan and classifier on received and sent mail, and PostHog, Sentry and Google Workspace. It also said the website's analytics never load without consent, while they are on by default outside the EEA, the UK and Switzerland. The vendor found the gap, corrected the list on 5 October and announced it in the changelog. A misleading claim, fixed and documented, so the minimum, -2, as agentos, svix and qwen-code took (https://mails.ai/sub-processors; https://mails.ai/changelog/sub-processors-ten-added-two-removed)" ], "verdict": "Per-agent addresses with scoped keys, a drafts-only scope, an injection score on every inbound message and MCP tools with safety hints. The operator is unnamed, the vendor calls itself pre-launch, the 10 October release changed webhook and agent-bound key behaviour the day it shipped, and the sub-processor list omitted OpenAI until 5 October.", "bestFor": "Agents that send transactional mail and read replies, such as support, notification and verification agents, where an injection score on inbound mail is wanted out of the box.", "strengths": [ "API keys scoped to send, read, manage or draft, bound to one agent if needed, with expiry and immediate revocation", "Every inbound message carries an injection score and a quarantined flag", "OpenAPI 3.1 spec, llms.txt, an errors page and documented rate limits, with 429s that say when the limit resets", "Free plan with 3,000 emails a month, no card, and test keys that send nothing", "MCP tools carry readOnly and destructive hints, and sends take an idempotency key" ], "weaknesses": [ "No company or person named; legal entity details only on request", "The 10 October release changed webhook, agent-bound key and 429 behaviour on the day it shipped", "Test keys could change, send or delete drafts created with a live key until an October 2026 fix, with no security advisory", "No SOC 2, no bug bounty, and a disclosure policy that doesn't commit to replying", "73 MCP tools for a full-access key, and MCP errors drop the API's error code" ], "agentNotes": [ "Use an `mk_test_` key until the flow works. Test keys run validation, the scanner, threading and webhooks without sending mail", "Skip inbound events where `quarantined` is true, and treat every other body as untrusted input", "Send an `Idempotency-Key` header on POST /v1/messages, or `idempotency_key` on the MCP send tools, so a retried send doesn't go out twice", "Mint a key with only the scopes the task needs, bound to one agent with `agent_id`, or a draft-scoped key when a person approves each send", "Name thread events explicitly on a webhook endpoint. Since 10 October a `*` subscription no longer receives them" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 65.2 } ], "editorialScores": { "ergonomics": 83, "maintenance": 80, "payments": 30, "reliability": 80, "schema": 84, "security": 78, "transparency": 57 }, "provenanceScore": 72, "checked": { "categories": { "ergonomics": "2026-11-01", "maintenance": "2026-11-01", "payments": "2026-11-01", "reliability": "2026-11-01", "schema": "2026-11-01", "security": "2026-11-01", "transparency": "2026-11-01" }, "last": "2026-11-01", "lastMoved": "2026-11-01", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "npm install @mailsai/sdk", "http": "curl -X POST https://api.mails.ai/v1/messages \\\n -H \"Authorization: Bearer mk_live_...\" \\\n -d '{\"from\":\"hello\",\"to\":\"lead@example.com\",\n \"subject\":\"Demo confirmation\",\n \"body_text\":\"Confirmed for Tuesday at 2pm ET.\"}'", "claudeCode": "claude mcp add --transport http mails https://api.mails.ai/mcp --header \"Authorization: Bearer mk_...\"", "config": { "mcpServers": { "mails": { "args": [ "-y", "-p", "@mailsai/mcp-server", "mails-mcp" ], "command": "npx", "env": { "MAILS_API_KEY": "mk_test_xxx" } } } } }, "letme": { "capability": "https://letme.dev/email.inbox", "tool": "https://letme.dev/mails-ai" }, "area": "communication", "unitPrices": [ { "item": "Pro plan", "unit": "month", "usd": 20, "note": "5 agents, 50,000 sends and 50,000 inbound a month, custom domains" }, { "item": "Scale plan", "unit": "month", "usd": 99, "note": "Unlimited agents, 250,000 sends and 500,000 inbound a month" } ], "provenance": { "legalEntity": "", "domain": "mails.ai", "domainRegistered": "2022-08-02", "endpointOnVendorDomain": true, "terms": "https://mails.ai/terms", "privacy": "https://mails.ai/privacy", "statusPage": "https://status.mails.ai", "changelog": "https://mails.ai/changelog", "securityTxt": "valid", "checked": "2026-10-05", "notes": [ "The terms (effective 14 May 2026) and the privacy policy call the operator Mails.ai and say legal entity details are available on request. The terms are governed by the law of England and Wales. Companies House shows no company named Mails.ai.", "RDAP for mails.ai gives a registration date of 2022-08-02, Namecheap as registrar and a privacy-masked registrant.", "The status page says support runs in business hours at UTC+8. Blog posts carry the byline 'Deepak' with no surname.", "mails.ai/.well-known/security.txt points to support@mails.ai and expires 2027-07-01.", "The API answers at api.mails.ai/v1 and the hosted MCP endpoint at api.mails.ai/mcp, both on the vendor's domain. The npm and PyPI packages and the GitHub org list mails.ai addresses." ], "score": 72 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/mails-ai.json", "live": { "slug": "mails-ai", "probe": { "target": "https://api.mails.ai/v1", "method": "get", "lastAt": "2026-11-07T22:56:07.475727329Z", "lastOk": true, "lastStatus": 404, "lastMs": 111, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 111, "p95ms24h": 249, "samples24h": 244, "samples30d": 7956, "days": [ { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 247 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "date": "2026-10-18", "probes": 256, "ok": 256 }, { "date": "2026-10-19", "probes": 255, "ok": 255 }, { "date": "2026-10-20", "probes": 252, "ok": 252 }, { "date": "2026-10-21", "probes": 253, "ok": 253 }, { "date": "2026-10-22", "probes": 253, "ok": 253 }, { "date": "2026-10-23", "probes": 248, "ok": 248 }, { "date": "2026-10-24", "probes": 251, "ok": 251 }, { "date": "2026-10-25", "probes": 250, "ok": 250 }, { "date": "2026-10-26", "probes": 252, "ok": 252 }, { "date": "2026-10-27", "probes": 249, "ok": 249 }, { "date": "2026-10-28", "probes": 251, "ok": 251 }, { "date": "2026-10-29", "probes": 248, "ok": 248 }, { "date": "2026-10-30", "probes": 249, "ok": 249 }, { "date": "2026-10-31", "probes": 251, "ok": 251 }, { "date": "2026-11-01", "probes": 249, "ok": 249 }, { "date": "2026-11-02", "probes": 250, "ok": 250 }, { "date": "2026-11-03", "probes": 248, "ok": 248 }, { "date": "2026-11-04", "probes": 246, "ok": 246 }, { "date": "2026-11-05", "probes": 185, "ok": 185 }, { "date": "2026-11-06", "probes": 241, "ok": 241 }, { "date": "2026-11-07", "probes": 233, "ok": 233 } ] }, "vendorStatus": { "page": "https://status.mails.ai", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-11-07T04:48:01.561194604Z" }, "versions": [ { "registry": "mcp-registry", "name": "ai.mails/agent-email", "version": "0.5.0", "seenAt": "2026-11-07T18:16:28.95801333Z" }, { "registry": "npm", "name": "@mailsai/mcp-server", "version": "0.6.0", "seenAt": "2026-11-06T23:42:06.903190155Z" }, { "registry": "npm", "name": "@mailsai/sdk", "version": "0.6.0", "seenAt": "2026-11-06T23:42:07.139891315Z" }, { "registry": "pypi", "name": "mailsai", "version": "0.6.0", "released": "2026-11-02", "seenAt": "2026-11-06T23:42:09.118282131Z" } ], "githubStars": 0, "npmWeekly": 344, "pypiWeekly": 145, "securityTxt": { "url": "https://mails.ai/.well-known/security.txt", "state": "valid", "expires": "2027-07-01T00:00:00.000Z", "checkedAt": "2026-11-07T15:59:50.603030454Z" }, "llmsTxt": { "url": "https://mails.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:32:56.501242122Z" }, "domain": { "domain": "mails.ai", "registered": "2022-08-02", "source": "https://rdap.identitydigital.services/rdap/domain/mails.ai", "checkedAt": "2026-11-01T14:23:01.333160406Z" }, "pages": [ { "url": "https://mails.ai/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:13:41.690902073Z", "changedAt": "2026-11-05T12:36:58.356267403Z", "fingerprint": "56d052b5ff1f" }, { "url": "https://mails.ai/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-11-07T14:13:43.98489527Z", "changedAt": "2026-11-05T12:37:00.551426259Z", "fingerprint": "b67b87a7f766" }, { "url": "https://mails.ai/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-07T14:13:46.077347782Z", "changedAt": "2026-11-05T12:37:02.641031632Z", "fingerprint": "ffc6f7b2a580" }, { "url": "https://mails.ai/terms", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:13:47.948570828Z", "changedAt": "2026-11-05T12:37:04.555537127Z", "fingerprint": "3734e3d71308" } ], "mcpTools": { "url": "https://api.mails.ai/mcp", "checkedAt": "2026-11-07T01:46:07.267374346Z", "status": "auth", "note": "asks for credentials before listing its tools", "changedAt": "2026-11-07T01:46:07.267374346Z" }, "github": { "repo": "mailsai/mailsai", "checkedAt": "2026-11-02T09:02:44.917132153Z", "stars": 0, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-19T20:00:00Z", "openIssues": 0, "openPRs": 0, "issuesOpened90d": 0, "issuesClosed90d": 0, "prsMerged90d": 0, "ci": { "branch": "main", "runs": 19, "success": 19, "failure": 0, "other": 0, "latest": "success", "latestAt": "2026-10-19T20:00:13Z" } }, "updatedAt": "2026-11-07T22:56:07.475727329Z" } }, "edges": [ { "by": 78, "category": "maintenance", "leads": "mails-ai", "name": "Maintenance \u0026 community", "reasons": { "a": "The last commit was on 1 April 2026, 219 days before this check (0). No releases or commits in the 90 days from 8 August (0). Issue and pull request activity couldn't be read through GitHub's API that day (0, unchecked). Not in the official MCP registry and no published package (0). Dependencies such as `agents` ^0.0.74 and the MCP SDK ^1.12.1 date from early 2026, and there's no CI (2 of 10). Total 2.", "b": "@mailsai/mcp-server 0.5.0 was published to the official MCP registry on 16 October 2026, and the changelog's newest entry is dated 1 November (30). Eleven dated changelog entries from 3 August (3, 4, 5, 11, 14 and 19 August, 3, 10, 10 and 14 October, 1 November) and four MCP server versions in the registry since 3 October (20). Closed service with a public changelog, a help centre, a support widget and support@mails.ai with a stated one-business-day reply. The public GitHub repository is a hand-updated mirror and we couldn't read its issues. We didn't test support (10 of 15). ai.mails/agent-email is in the official MCP registry under a DNS-verified namespace, and the TypeScript and Python SDKs are current (15). Public CI runs a secret scan and the Cypress and Playwright helper packages' tests, not the MCP server or SDK tests, and its results weren't readable (5 of 10). 30 + 20 + 10 + 15 + 5 = 80." }, "scores": { "a": 2, "b": 80 } }, { "by": 72, "category": "reliability", "leads": "mails-ai", "name": "Reliability", "reasons": { "a": "Graded with the lines for self-hosted software, since each deployer runs their own Worker. No published package; it deploys from the repository with a Deploy to Cloudflare button, Bun and Wrangler, and states the Cloudflare products it needs (8 of 20). No CI workflow or test suite in the repository (0). Open issues couldn't be read, because GitHub's API refused our requests for its rate limit, so the line scores absent (0, unchecked). No tags, releases or changelog; package.json says 0.1.0 (0). Pre-1.0 (0). Total 8.", "b": "Graded as a hosted service. Better Stack status page at status.mails.ai with API, dashboard and website components and 90-day bars (20). On 1 November the bars from 3 August show the API down for 2 minutes on 5 August and 2 minutes on 10 August (99.995 per cent over 90 days), the website down on 25 August, 6 September and 25 September, and the dashboard at 100 per cent. The July downtime read on 5 October has left the window. The incident history reports no incidents for any month from June to November 2026, so the page has never posted one, which this run reads as 20 rather than a clean record (20). Send caps published per plan by hour, day and month (15). 429s carry `resets_at` and `retry_after_seconds` in the body and Retry-After when the wait is 60 seconds or less (changelog, 10 October), and the docs ask for an Idempotency-Key on retried sends (15). A 99.9 per cent uptime target with pro-rated credit is on mails.ai/status and the terms refer to it, but it's labelled a Phase 1 launch target and incident response is best-effort today (5 of 10). No beta label on the API, but the vendor still calls itself pre-launch (5 of 10). 20 + 20 + 15 + 15 + 5 + 5 = 80." }, "scores": { "a": 8, "b": 80 } }, { "by": 36, "category": "security", "leads": "mails-ai", "name": "Security \u0026 auth", "reasons": { "a": "One shared secret for REST and MCP, compared in constant time, with no scopes, expiry or per-client keys (10 of 30). Sender approval, drafts, and an optional allowlist of domains for routing changes limit what an agent can see and change; the key can still send to anyone (14 of 20). Mail from unapproved senders is hidden from all query tools by default, and `list_pending` returns metadata without bodies, documented as a prompt-injection guard (15). No log of API or tool calls beyond the stored messages (3 of 15). No security policy, advisories or disclosure route for this personal project (0). Total 42.", "b": "Bearer keys, scoped to send, read, manage or (since 10 October) draft, bindable to one agent, with optional expiry, stored hashed and revocable at once by API; AI clients connecting to the hosted MCP endpoint sign in by OAuth, and connected apps can be listed and revoked (30). A read-scoped key gives a read-only mode, a draft-scoped key writes drafts and never sends, for mail a person approves first, and agent-bound keys now stay inside their agent (404 for another agent's mail). Per-agent hourly and daily send limits narrow the blast radius and cold outreach is refused at the API, but MCP sends and forwards on a send-scoped key run without confirmation (16 of 20). Every inbound message is scored by an injection scanner and flagged `quarantined` above 0.95, which the docs tell the agent to branch on. The scanner's accuracy is a vendor claim we didn't test (13 of 15). Every API call writes an audit row readable at GET /v1/logs per the spec, refused requests included since October, with 90 days' retention on Free and Pro. We didn't call it (12 of 15). security.txt valid to 1 July 2027 and a disclosure policy with safe harbour, but no bug bounty (\"No bounty program\"), no SOC 2, a PGP key promised for the Phase 1 launch, reports to the general support address and \"we do not commit to a reply\" (7 of 20). 30 + 16 + 13 + 12 + 7 = 78." }, "scores": { "a": 42, "b": 78 } }, { "by": 33, "category": "transparency", "leads": "mails-ai", "name": "Transparency \u0026 trust", "reasons": { "a": "The README and SKILL.md say MIT, but no LICENSE file is committed (20 of 30). Self-hosted; the README says mail is stored in the deployer's D1 database with attachments in R2 and sent through Cloudflare Email Service or Resend. No retention or deletion guidance (15 of 30). No deprecation policy (0). No telemetry in the source read; the only outbound calls are to the configured mail provider, Cloudflare's API and the deployer's own webhooks (15 of 20). Total 50.", "b": "The MCP server and SDKs are MIT and the API is closed. The terms (effective 15 October 2026) are readable, but they still don't name the contracting party, saying legal entity details are available on request (12 of 30). Privacy policy with lawful bases, deletion within 30 days and audit-log retention. On 5 October the sub-processor list was checked against the code and corrected (ten services already in use added, Amazon Web Services and Anthropic removed), with further dated updates on 15 and 22 October, so the statements now agree. DPA on request, no named controller (20 of 30). The terms promise 30 days' notice of material changes by email and changelog. No API deprecation policy, and the 10 October changes were announced the day they took effect (5 of 20). Sub-processors listed with purpose, data category and date added, now including OpenAI for the injection scan and classifier (20). 12 + 20 + 5 + 20 = 57." }, "scores": { "a": 32, "b": 65 } }, { "by": 30, "category": "schema", "leads": "mails-ai", "name": "Schema \u0026 documentation", "reasons": { "a": "All 21 MCP tools take typed zod inputs, which the MCP SDK publishes as JSON Schema (25). SKILL.md and AGENTS.md give agent-readable setup in Markdown; no llms.txt (5 of 10). Descriptions are one line each, such as `Send an email`, with parameter descriptions but no when-not-to-use (8 of 20). Inputs are typed with defaults for limit and offset, but recipients are a comma-separated string and direction isn't an enum in the schema read (9 of 15). The README has request examples and a REST route table; error responses aren't documented (7 of 15). No versioning or changelog (0). Total 54.", "b": "OpenAPI 3.1 at api.mails.ai/v1/openapi.json with a required scope per operation (57 operations on 5 October; the MCP server's generated file says the API document had 74 on 17 October), and typed JSON Schema inputs on every MCP tool (25). llms.txt with a page index; the docs have no Markdown twins (10). MCP descriptions run from one line to a paragraph for mails_send and mails_test_inbound, and few say when not to call (10 of 20). Required fields and enums on status, pool_hint, spf and dkim, but no bounds on `limit` and free-form `to` (string or array) (10 of 15). An errors page with one envelope (type, code, message, param, request_id), curl examples in the quickstart and limits pages, and examples in the spec (14 of 15). A dated changelog with eleven entries from 3 August to 1 November and a /v1 API. llms.txt no longer gives a five-tool count or a Python SDK still to come, and the terms (effective 15 October) no longer describe a metered tier, so the docs now agree with each other (15). 25 + 10 + 10 + 10 + 14 + 15 = 84." }, "scores": { "a": 54, "b": 84 } }, { "by": 30, "category": "ergonomics", "leads": "mails-ai", "name": "Agent ergonomics", "reasons": { "a": "21 tools, the 11 to 30 band (15 of 25). List and search tools take limit, offset and filters by direction, sender, label and archive state (20). Error shapes aren't documented; the code returns JSON errors (8 of 20). No idempotency key for sends and no readOnlyHint or destructiveHint annotations; drafts give a review step (3 of 20). Archived mail is excluded by default and the CLI has a `--json` mode, but there's no SDK beyond the CLI (7 of 15). Total 53.", "b": "Since @mailsai/mcp-server 0.3.0 (10 October) every API operation but four is a tool, 73 in 0.5.0 (20 written by hand, 53 generated), which is the over-30 band (5). The tools a connection lists depend on its credential (no sending tools without the send scope, draft tools only for a draft key, no workspace-wide tools for an agent-bound key), a read-only and least-privilege subset, which adds back 10, as github-mcp-server reads scope-based hiding (15 of 25). Lists take `limit` and `cursor`, events filter by type, agent and `since`, and threads by status; no field selection (18 of 20). REST errors carry stable codes, `param` and Retry-After. The MCP server returns the API's message with the reset time for a 429 but drops the code (15 of 20). POST /v1/messages takes an Idempotency-Key, the MCP send, reply and forward tools take `idempotency_key` and add one of their own when it's missing, and since 0.4.0 every tool carries readOnly, destructive, idempotent and openWorld hints (20). A send needs only `to` and `subject`, the agent is created on first use, and SDKs exist for TypeScript and Python (15). 15 + 18 + 15 + 20 + 15 = 83." }, "scores": { "a": 53, "b": 83 } } ], "facts": [ { "a": "MCP server", "b": "HTTP API", "name": "Kind" }, { "a": "Frank Harris", "b": "Mails.ai", "name": "Vendor" }, { "a": "no (local only)", "b": "https://api.mails.ai/v1", "name": "Hosted endpoint" }, { "a": "Streamable HTTP, HTTP", "b": "HTTP, Streamable HTTP, stdio", "name": "Transports" }, { "a": "API key", "b": "API key", "name": "Auth" }, { "a": "Free", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "MIT", "b": "Proprietary hosted API under the mails.ai terms of service. The MCP server, the TypeScript SDK and the Python SDK in mailsai/mailsai are MIT", "name": "Licence" }, { "a": "21", "b": "73", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "not listed", "b": "ai.mails/agent-email", "name": "MCP registry" }, { "a": "2026-04-01", "b": "2026-10-16", "name": "Last release" }, { "a": "no document linked", "b": "2026-05-14", "name": "Terms last updated" }, { "a": "no document linked", "b": "2026-05-14", "name": "Privacy policy last updated" }, { "a": "not read yet", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not read yet", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "650 npm/wk, 116 PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "3.5/5 (2)", "name": "Agent reviews" } ], "faq": [ { "answer": "mails.ai Agent Email scores 65.2 (B) on agent readiness against Clawpost's 36.8 (F), and leads in 6 of 7 scored categories. Clawpost leads on payments \u0026 pricing.", "question": "Which is better for AI agents, Clawpost or mails.ai Agent Email?" }, { "answer": "Both need an API key.", "question": "Do Clawpost and mails.ai Agent Email need an API key?" }, { "answer": "No hosted endpoint is listed for Clawpost. mails.ai Agent Email has a hosted endpoint at https://api.mails.ai/v1.", "question": "Can an agent call Clawpost and mails.ai Agent Email without installing anything?" }, { "answer": "Clawpost is open source (MIT). No open-source release is listed for mails.ai Agent Email.", "question": "Are Clawpost and mails.ai Agent Email open source?" } ], "goodFor": [ { "aheadOn": [ "Payments \u0026 pricing, 60 against 30" ], "also": [ "Open source", "No incidents deducted, where mails.ai Agent Email loses 8 points for them" ], "goodFor": "A developer who wants an agent inbox on their own domain and Cloudflare account with a default approval gate.", "slug": "clawpost", "watchFor": "One shared API key grants every REST and MCP operation; no scopes or read-only key" }, { "aheadOn": [ "Reliability, 80 against 8", "Schema \u0026 documentation, 84 against 54", "Agent ergonomics, 83 against 53", "Security \u0026 auth, 78 against 42", "Maintenance \u0026 community, 80 against 2", "Transparency \u0026 trust, 65 against 32" ], "also": [ "A hosted endpoint, with nothing to install", "Runs on your own machine", "Free to start without a card" ], "goodFor": "Agents that send transactional mail and read replies, such as support, notification and verification agents, where an injection score on inbound mail is wanted out of the box.", "slug": "mails-ai", "watchFor": "No company or person named; legal entity details only on request" } ], "history": { "clawpost": null, "mails-ai": [ { "causes": [ "product", "event", "time" ], "date": "2026-11-01", "delta": -1.6, "from": 66.8, "fromGrade": "B", "to": 65.2, "toGrade": "B" }, { "causes": [ "correction" ], "date": "2026-10-28", "delta": -0.1, "from": 66.9, "fromGrade": "B", "to": 66.8, "toGrade": "B" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.2, "from": 66.7, "fromGrade": "B", "to": 66.9, "toGrade": "B" } ] }, "job": { "capability": "email.inbox", "name": "Agent inboxes" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agentmail-vs-clawpost.json", "title": "AgentMail API + MCP vs Clawpost", "url": "https://www.anchorterminal.com/compare/agentmail-vs-clawpost" }, { "json": "https://www.anchorterminal.com/compare/agentmail-vs-mails-ai.json", "title": "AgentMail API + MCP vs mails.ai Agent Email", "url": "https://www.anchorterminal.com/compare/agentmail-vs-mails-ai" }, { "json": "https://www.anchorterminal.com/compare/cherami-vs-clawpost.json", "title": "Cherami vs Clawpost", "url": "https://www.anchorterminal.com/compare/cherami-vs-clawpost" }, { "json": "https://www.anchorterminal.com/compare/cherami-vs-mails-ai.json", "title": "Cherami vs mails.ai Agent Email", "url": "https://www.anchorterminal.com/compare/cherami-vs-mails-ai" }, { "json": "https://www.anchorterminal.com/compare/clawpost-vs-hostinger-agentic-mail.json", "title": "Clawpost vs Hostinger Agentic Mail", "url": "https://www.anchorterminal.com/compare/clawpost-vs-hostinger-agentic-mail" }, { "json": "https://www.anchorterminal.com/compare/clawpost-vs-inbound.json", "title": "Clawpost vs Inbound", "url": "https://www.anchorterminal.com/compare/clawpost-vs-inbound" }, { "json": "https://www.anchorterminal.com/compare/clawpost-vs-inboxapi.json", "title": "Clawpost vs InboxAPI", "url": "https://www.anchorterminal.com/compare/clawpost-vs-inboxapi" }, { "json": "https://www.anchorterminal.com/compare/clawpost-vs-lumbox.json", "title": "Clawpost vs Lumbox", "url": "https://www.anchorterminal.com/compare/clawpost-vs-lumbox" }, { "json": "https://www.anchorterminal.com/compare/clawpost-vs-mailows.json", "title": "Clawpost vs Mailows", "url": "https://www.anchorterminal.com/compare/clawpost-vs-mailows" }, { "json": "https://www.anchorterminal.com/compare/clawpost-vs-mailslurp.json", "title": "Clawpost vs MailSlurp", "url": "https://www.anchorterminal.com/compare/clawpost-vs-mailslurp" }, { "json": "https://www.anchorterminal.com/compare/clawpost-vs-postfleet.json", "title": "Clawpost vs Postfleet", "url": "https://www.anchorterminal.com/compare/clawpost-vs-postfleet" }, { "json": "https://www.anchorterminal.com/compare/clawpost-vs-robotomail.json", "title": "Clawpost vs Robotomail", "url": "https://www.anchorterminal.com/compare/clawpost-vs-robotomail" }, { "json": "https://www.anchorterminal.com/compare/hostinger-agentic-mail-vs-mails-ai.json", "title": "Hostinger Agentic Mail vs mails.ai Agent Email", "url": "https://www.anchorterminal.com/compare/hostinger-agentic-mail-vs-mails-ai" }, { "json": "https://www.anchorterminal.com/compare/inbound-vs-mails-ai.json", "title": "Inbound vs mails.ai Agent Email", "url": "https://www.anchorterminal.com/compare/inbound-vs-mails-ai" }, { "json": "https://www.anchorterminal.com/compare/inboxapi-vs-mails-ai.json", "title": "InboxAPI vs mails.ai Agent Email", "url": "https://www.anchorterminal.com/compare/inboxapi-vs-mails-ai" }, { "json": "https://www.anchorterminal.com/compare/lumbox-vs-mails-ai.json", "title": "Lumbox vs mails.ai Agent Email", "url": "https://www.anchorterminal.com/compare/lumbox-vs-mails-ai" }, { "json": "https://www.anchorterminal.com/compare/mailows-vs-mails-ai.json", "title": "Mailows vs mails.ai Agent Email", "url": "https://www.anchorterminal.com/compare/mailows-vs-mails-ai" }, { "json": "https://www.anchorterminal.com/compare/mails-ai-vs-mailslurp.json", "title": "mails.ai Agent Email vs MailSlurp", "url": "https://www.anchorterminal.com/compare/mails-ai-vs-mailslurp" }, { "json": "https://www.anchorterminal.com/compare/mails-ai-vs-postfleet.json", "title": "mails.ai Agent Email vs Postfleet", "url": "https://www.anchorterminal.com/compare/mails-ai-vs-postfleet" }, { "json": "https://www.anchorterminal.com/compare/mails-ai-vs-robotomail.json", "title": "mails.ai Agent Email vs Robotomail", "url": "https://www.anchorterminal.com/compare/mails-ai-vs-robotomail" } ], "panel": null, "scores": [ { "by": 72, "clawpost": 8, "edge": "mails-ai", "key": "reliability", "mails-ai": 80, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 30, "clawpost": 54, "edge": "mails-ai", "key": "schema", "mails-ai": 84, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 30, "clawpost": 53, "edge": "mails-ai", "key": "ergonomics", "mails-ai": 83, "name": "Agent ergonomics", "weight": 13 }, { "by": 36, "clawpost": 42, "edge": "mails-ai", "key": "security", "mails-ai": 78, "name": "Security \u0026 auth", "weight": 14 }, { "by": 30, "clawpost": 60, "edge": "clawpost", "key": "payments", "mails-ai": 30, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 78, "clawpost": 2, "edge": "mails-ai", "key": "maintenance", "mails-ai": 80, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 33, "clawpost": 32, "edge": "mails-ai", "key": "transparency", "mails-ai": 65, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "mails.ai Agent Email scores 65.2 (B) on agent readiness against Clawpost's 36.8 (F), and leads in 6 of 7 scored categories. Clawpost leads on payments \u0026 pricing. Both do agent inboxes.", "tasks": null, "tutorials": [], "verdicts": { "clawpost": "A small self-hosted agent inbox whose sender-approval gate keeps unknown senders' mail away from the agent by default, with drafts for human review. It is one developer's project, unchanged since 1 April 2026, with one all-powerful key, no releases, tests or CI.", "mails-ai": "Per-agent addresses with scoped keys, a drafts-only scope, an injection score on every inbound message and MCP tools with safety hints. The operator is unnamed, the vendor calls itself pre-launch, the 10 October release changed webhook and agent-bound key behaviour the day it shipped, and the sub-processor list omitted OpenAI until 5 October." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/clawpost-vs-mails-ai", "json": "https://www.anchorterminal.com/compare/clawpost-vs-mails-ai.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/clawpost-vs-mails-ai.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/clawpost-vs-mails-ai.min.md" }, "markdown": "mails.ai Agent Email scores 65.2 (B) on agent readiness against Clawpost's 36.8 (F), and leads in 6 of 7 scored categories. Clawpost leads on payments \u0026 pricing. Both do agent inboxes.\n\n- Clawpost: grade F, 36.8/100, rank #1383 of 1510. Markdown https://www.anchorterminal.com/tools/clawpost.md · JSON https://www.anchorterminal.com/api/v1/tools/clawpost.json\n- mails.ai Agent Email: grade B, 65.2/100, rank #434 of 1510. Markdown https://www.anchorterminal.com/tools/mails-ai.md · JSON https://www.anchorterminal.com/api/v1/tools/mails-ai.json\n- Best email inbox APIs for AI agents: https://www.anchorterminal.com/best/agent-inboxes/index.md\n- All 66 inboxes comparisons: https://www.anchorterminal.com/compare/agent-inboxes/index.md\n\n## Which one, for what\n\n### Clawpost (F)\n\nGood for: A developer who wants an agent inbox on their own domain and Cloudflare account with a default approval gate.\n\nAhead on:\n- Payments \u0026 pricing, 60 against 30\n\nAlso in its favour:\n- Open source\n- No incidents deducted, where mails.ai Agent Email loses 8 points for them\n\nWatch for: One shared API key grants every REST and MCP operation; no scopes or read-only key\n\n### mails.ai Agent Email (B)\n\nGood for: Agents that send transactional mail and read replies, such as support, notification and verification agents, where an injection score on inbound mail is wanted out of the box.\n\nAhead on:\n- Reliability, 80 against 8\n- Schema \u0026 documentation, 84 against 54\n- Agent ergonomics, 83 against 53\n- Security \u0026 auth, 78 against 42\n- Maintenance \u0026 community, 80 against 2\n- Transparency \u0026 trust, 65 against 32\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n- Runs on your own machine\n- Free to start without a card\n\nWatch for: No company or person named; legal entity details only on request\n\n\n## Why the edge\n\n### Maintenance \u0026 community: mails.ai Agent Email +78\n\n- Clawpost (2): The last commit was on 1 April 2026, 219 days before this check (0). No releases or commits in the 90 days from 8 August (0). Issue and pull request activity couldn't be read through GitHub's API that day (0, unchecked). Not in the official MCP registry and no published package (0). Dependencies such as `agents` ^0.0.74 and the MCP SDK ^1.12.1 date from early 2026, and there's no CI (2 of 10). Total 2.\n- mails.ai Agent Email (80): @mailsai/mcp-server 0.5.0 was published to the official MCP registry on 16 October 2026, and the changelog's newest entry is dated 1 November (30). Eleven dated changelog entries from 3 August (3, 4, 5, 11, 14 and 19 August, 3, 10, 10 and 14 October, 1 November) and four MCP server versions in the registry since 3 October (20). Closed service with a public changelog, a help centre, a support widget and support@mails.ai with a stated one-business-day reply. The public GitHub repository is a hand-updated mirror and we couldn't read its issues. We didn't test support (10 of 15). ai.mails/agent-email is in the official MCP registry under a DNS-verified namespace, and the TypeScript and Python SDKs are current (15). Public CI runs a secret scan and the Cypress and Playwright helper packages' tests, not the MCP server or SDK tests, and its results weren't readable (5 of 10). 30 + 20 + 10 + 15 + 5 = 80.\n\n### Reliability: mails.ai Agent Email +72\n\n- Clawpost (8): Graded with the lines for self-hosted software, since each deployer runs their own Worker. No published package; it deploys from the repository with a Deploy to Cloudflare button, Bun and Wrangler, and states the Cloudflare products it needs (8 of 20). No CI workflow or test suite in the repository (0). Open issues couldn't be read, because GitHub's API refused our requests for its rate limit, so the line scores absent (0, unchecked). No tags, releases or changelog; package.json says 0.1.0 (0). Pre-1.0 (0). Total 8.\n- mails.ai Agent Email (80): Graded as a hosted service. Better Stack status page at status.mails.ai with API, dashboard and website components and 90-day bars (20). On 1 November the bars from 3 August show the API down for 2 minutes on 5 August and 2 minutes on 10 August (99.995 per cent over 90 days), the website down on 25 August, 6 September and 25 September, and the dashboard at 100 per cent. The July downtime read on 5 October has left the window. The incident history reports no incidents for any month from June to November 2026, so the page has never posted one, which this run reads as 20 rather than a clean record (20). Send caps published per plan by hour, day and month (15). 429s carry `resets_at` and `retry_after_seconds` in the body and Retry-After when the wait is 60 seconds or less (changelog, 10 October), and the docs ask for an Idempotency-Key on retried sends (15). A 99.9 per cent uptime target with pro-rated credit is on mails.ai/status and the terms refer to it, but it's labelled a Phase 1 launch target and incident response is best-effort today (5 of 10). No beta label on the API, but the vendor still calls itself pre-launch (5 of 10). 20 + 20 + 15 + 15 + 5 + 5 = 80.\n\n### Security \u0026 auth: mails.ai Agent Email +36\n\n- Clawpost (42): One shared secret for REST and MCP, compared in constant time, with no scopes, expiry or per-client keys (10 of 30). Sender approval, drafts, and an optional allowlist of domains for routing changes limit what an agent can see and change; the key can still send to anyone (14 of 20). Mail from unapproved senders is hidden from all query tools by default, and `list_pending` returns metadata without bodies, documented as a prompt-injection guard (15). No log of API or tool calls beyond the stored messages (3 of 15). No security policy, advisories or disclosure route for this personal project (0). Total 42.\n- mails.ai Agent Email (78): Bearer keys, scoped to send, read, manage or (since 10 October) draft, bindable to one agent, with optional expiry, stored hashed and revocable at once by API; AI clients connecting to the hosted MCP endpoint sign in by OAuth, and connected apps can be listed and revoked (30). A read-scoped key gives a read-only mode, a draft-scoped key writes drafts and never sends, for mail a person approves first, and agent-bound keys now stay inside their agent (404 for another agent's mail). Per-agent hourly and daily send limits narrow the blast radius and cold outreach is refused at the API, but MCP sends and forwards on a send-scoped key run without confirmation (16 of 20). Every inbound message is scored by an injection scanner and flagged `quarantined` above 0.95, which the docs tell the agent to branch on. The scanner's accuracy is a vendor claim we didn't test (13 of 15). Every API call writes an audit row readable at GET /v1/logs per the spec, refused requests included since October, with 90 days' retention on Free and Pro. We didn't call it (12 of 15). security.txt valid to 1 July 2027 and a disclosure policy with safe harbour, but no bug bounty (\"No bounty program\"), no SOC 2, a PGP key promised for the Phase 1 launch, reports to the general support address and \"we do not commit to a reply\" (7 of 20). 30 + 16 + 13 + 12 + 7 = 78.\n\n### Transparency \u0026 trust: mails.ai Agent Email +33\n\n- Clawpost (32): The README and SKILL.md say MIT, but no LICENSE file is committed (20 of 30). Self-hosted; the README says mail is stored in the deployer's D1 database with attachments in R2 and sent through Cloudflare Email Service or Resend. No retention or deletion guidance (15 of 30). No deprecation policy (0). No telemetry in the source read; the only outbound calls are to the configured mail provider, Cloudflare's API and the deployer's own webhooks (15 of 20). Total 50.\n- mails.ai Agent Email (65): The MCP server and SDKs are MIT and the API is closed. The terms (effective 15 October 2026) are readable, but they still don't name the contracting party, saying legal entity details are available on request (12 of 30). Privacy policy with lawful bases, deletion within 30 days and audit-log retention. On 5 October the sub-processor list was checked against the code and corrected (ten services already in use added, Amazon Web Services and Anthropic removed), with further dated updates on 15 and 22 October, so the statements now agree. DPA on request, no named controller (20 of 30). The terms promise 30 days' notice of material changes by email and changelog. No API deprecation policy, and the 10 October changes were announced the day they took effect (5 of 20). Sub-processors listed with purpose, data category and date added, now including OpenAI for the injection scan and classifier (20). 12 + 20 + 5 + 20 = 57.\n\n### Schema \u0026 documentation: mails.ai Agent Email +30\n\n- Clawpost (54): All 21 MCP tools take typed zod inputs, which the MCP SDK publishes as JSON Schema (25). SKILL.md and AGENTS.md give agent-readable setup in Markdown; no llms.txt (5 of 10). Descriptions are one line each, such as `Send an email`, with parameter descriptions but no when-not-to-use (8 of 20). Inputs are typed with defaults for limit and offset, but recipients are a comma-separated string and direction isn't an enum in the schema read (9 of 15). The README has request examples and a REST route table; error responses aren't documented (7 of 15). No versioning or changelog (0). Total 54.\n- mails.ai Agent Email (84): OpenAPI 3.1 at api.mails.ai/v1/openapi.json with a required scope per operation (57 operations on 5 October; the MCP server's generated file says the API document had 74 on 17 October), and typed JSON Schema inputs on every MCP tool (25). llms.txt with a page index; the docs have no Markdown twins (10). MCP descriptions run from one line to a paragraph for mails_send and mails_test_inbound, and few say when not to call (10 of 20). Required fields and enums on status, pool_hint, spf and dkim, but no bounds on `limit` and free-form `to` (string or array) (10 of 15). An errors page with one envelope (type, code, message, param, request_id), curl examples in the quickstart and limits pages, and examples in the spec (14 of 15). A dated changelog with eleven entries from 3 August to 1 November and a /v1 API. llms.txt no longer gives a five-tool count or a Python SDK still to come, and the terms (effective 15 October) no longer describe a metered tier, so the docs now agree with each other (15). 25 + 10 + 10 + 10 + 14 + 15 = 84.\n\n### Agent ergonomics: mails.ai Agent Email +30\n\n- Clawpost (53): 21 tools, the 11 to 30 band (15 of 25). List and search tools take limit, offset and filters by direction, sender, label and archive state (20). Error shapes aren't documented; the code returns JSON errors (8 of 20). No idempotency key for sends and no readOnlyHint or destructiveHint annotations; drafts give a review step (3 of 20). Archived mail is excluded by default and the CLI has a `--json` mode, but there's no SDK beyond the CLI (7 of 15). Total 53.\n- mails.ai Agent Email (83): Since @mailsai/mcp-server 0.3.0 (10 October) every API operation but four is a tool, 73 in 0.5.0 (20 written by hand, 53 generated), which is the over-30 band (5). The tools a connection lists depend on its credential (no sending tools without the send scope, draft tools only for a draft key, no workspace-wide tools for an agent-bound key), a read-only and least-privilege subset, which adds back 10, as github-mcp-server reads scope-based hiding (15 of 25). Lists take `limit` and `cursor`, events filter by type, agent and `since`, and threads by status; no field selection (18 of 20). REST errors carry stable codes, `param` and Retry-After. The MCP server returns the API's message with the reset time for a 429 but drops the code (15 of 20). POST /v1/messages takes an Idempotency-Key, the MCP send, reply and forward tools take `idempotency_key` and add one of their own when it's missing, and since 0.4.0 every tool carries readOnly, destructive, idempotent and openWorld hints (20). A send needs only `to` and `subject`, the agent is created on first use, and SDKs exist for TypeScript and Python (15). 15 + 18 + 15 + 20 + 15 = 83.\n\n## Score by category\n\n| Category | Weight | Clawpost | mails.ai Agent Email | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 8 | 80 | mails.ai Agent Email +72 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 54 | 84 | mails.ai Agent Email +30 |\n| Agent ergonomics | 13% (16.2 this run) | 53 | 83 | mails.ai Agent Email +30 |\n| Security \u0026 auth | 14% (17.5 this run) | 42 | 78 | mails.ai Agent Email +36 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 30 | Clawpost +30 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 2 | 80 | mails.ai Agent Email +78 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 32 | 65 | mails.ai Agent Email +33 |\n| Negative events | ≤15 | 0 | -8 | |\n| **Total** | | **36.8 · F** | **65.2 · B** | |\n\n## Facts side by side\n\n| Fact | Clawpost | mails.ai Agent Email |\n| --- | --- | --- |\n| Kind | MCP server | HTTP API |\n| Vendor | Frank Harris | Mails.ai |\n| Hosted endpoint | no (local only) | `https://api.mails.ai/v1` |\n| Transports | Streamable HTTP, HTTP | HTTP, Streamable HTTP, stdio |\n| Auth | API key | API key |\n| Pricing | Free | Freemium |\n| x402 | no | no |\n| Licence | MIT | Proprietary hosted API under the mails.ai terms of service. The MCP server, the TypeScript SDK and the Python SDK in mailsai/mailsai are MIT |\n| Tools exposed | 21 | 73 |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| MCP registry | not listed | `ai.mails/agent-email` |\n| Last release | 2026-04-01 | 2026-10-16 |\n| Terms last updated | no document linked | 2026-05-14 |\n| Privacy policy last updated | no document linked | 2026-05-14 |\n| Customer content may train models | not read yet | not found in the text |\n| Terms restrict automated access | not read yet | not found in the text |\n| Terms restrict benchmarking | not read yet | not found in the text |\n| Terms or service can change without notice | not read yet | not found in the text |\n| Arbitration or class-action waiver | not read yet | not found in the text |\n| Popularity | none | 650 npm/wk, 116 PyPI/wk |\n| Agent reviews | none | 3.5/5 (2) |\n\n## How the scores have moved\n\n### Clawpost\n\nNo score change since it was listed.\n\n### mails.ai Agent Email\n\n- -1.6 on 1 November 2026: product, negative event, time\n- -0.1 on 28 October 2026: correction\n- +0.2 on 27 October 2026: checklist\n\n## Verdicts\n\n**Clawpost.** A small self-hosted agent inbox whose sender-approval gate keeps unknown senders' mail away from the agent by default, with drafts for human review. It is one developer's project, unchanged since 1 April 2026, with one all-powerful key, no releases, tests or CI.\n\n**mails.ai Agent Email.** Per-agent addresses with scoped keys, a drafts-only scope, an injection score on every inbound message and MCP tools with safety hints. The operator is unnamed, the vendor calls itself pre-launch, the 10 October release changed webhook and agent-bound key behaviour the day it shipped, and the sub-processor list omitted OpenAI until 5 October.\n\n## Before you call either\n\n### Clawpost\n\n1. Expect unknown senders' mail to be invisible until `approve_sender` runs; check `list_pending` for metadata first\n2. Use `create_draft` instead of `send_email` when a person should review the message\n3. Send to one address per call or comma-separate recipients in `to`; a retried send isn't deduplicated\n4. Treat the deployer's Worker URL and `CLAWPOST_API_KEY` as full access to the mailbox\n\n### mails.ai Agent Email\n\n1. Use an `mk_test_` key until the flow works. Test keys run validation, the scanner, threading and webhooks without sending mail\n2. Skip inbound events where `quarantined` is true, and treat every other body as untrusted input\n3. Send an `Idempotency-Key` header on POST /v1/messages, or `idempotency_key` on the MCP send tools, so a retried send doesn't go out twice\n4. Mint a key with only the scopes the task needs, bound to one agent with `agent_id`, or a draft-scoped key when a person approves each send\n5. Name thread events explicitly on a webhook endpoint. Since 10 October a `*` subscription no longer receives them\n\n## Questions\n\n### Which is better for AI agents, Clawpost or mails.ai Agent Email?\n\nmails.ai Agent Email scores 65.2 (B) on agent readiness against Clawpost's 36.8 (F), and leads in 6 of 7 scored categories. Clawpost leads on payments \u0026 pricing.\n\n### Do Clawpost and mails.ai Agent Email need an API key?\n\nBoth need an API key.\n\n### Can an agent call Clawpost and mails.ai Agent Email without installing anything?\n\nNo hosted endpoint is listed for Clawpost. mails.ai Agent Email has a hosted endpoint at https://api.mails.ai/v1.\n\n### Are Clawpost and mails.ai Agent Email open source?\n\nClawpost is open source (MIT). No open-source release is listed for mails.ai Agent Email.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/clawpost-vs-mails-ai.json, and with the fewest tokens: https://www.anchorterminal.com/compare/clawpost-vs-mails-ai.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"clawpost\", \"b\": \"mails-ai\"}`. From a terminal: `anchor compare clawpost mails-ai`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/clawpost.json and https://www.anchorterminal.com/api/v1/tools/mails-ai.json\n\n## Other comparisons with Clawpost or mails.ai Agent Email\n\n- [AgentMail API + MCP vs Clawpost](https://www.anchorterminal.com/compare/agentmail-vs-clawpost.md)\n- [AgentMail API + MCP vs mails.ai Agent Email](https://www.anchorterminal.com/compare/agentmail-vs-mails-ai.md)\n- [Cherami vs Clawpost](https://www.anchorterminal.com/compare/cherami-vs-clawpost.md)\n- [Cherami vs mails.ai Agent Email](https://www.anchorterminal.com/compare/cherami-vs-mails-ai.md)\n- [Clawpost vs Hostinger Agentic Mail](https://www.anchorterminal.com/compare/clawpost-vs-hostinger-agentic-mail.md)\n- [Clawpost vs Inbound](https://www.anchorterminal.com/compare/clawpost-vs-inbound.md)\n- [Clawpost vs InboxAPI](https://www.anchorterminal.com/compare/clawpost-vs-inboxapi.md)\n- [Clawpost vs Lumbox](https://www.anchorterminal.com/compare/clawpost-vs-lumbox.md)\n- [Clawpost vs Mailows](https://www.anchorterminal.com/compare/clawpost-vs-mailows.md)\n- [Clawpost vs MailSlurp](https://www.anchorterminal.com/compare/clawpost-vs-mailslurp.md)\n- [Clawpost vs Postfleet](https://www.anchorterminal.com/compare/clawpost-vs-postfleet.md)\n- [Clawpost vs Robotomail](https://www.anchorterminal.com/compare/clawpost-vs-robotomail.md)\n- [Hostinger Agentic Mail vs mails.ai Agent Email](https://www.anchorterminal.com/compare/hostinger-agentic-mail-vs-mails-ai.md)\n- [Inbound vs mails.ai Agent Email](https://www.anchorterminal.com/compare/inbound-vs-mails-ai.md)\n- [InboxAPI vs mails.ai Agent Email](https://www.anchorterminal.com/compare/inboxapi-vs-mails-ai.md)\n- [Lumbox vs mails.ai Agent Email](https://www.anchorterminal.com/compare/lumbox-vs-mails-ai.md)\n- [Mailows vs mails.ai Agent Email](https://www.anchorterminal.com/compare/mailows-vs-mails-ai.md)\n- [mails.ai Agent Email vs MailSlurp](https://www.anchorterminal.com/compare/mails-ai-vs-mailslurp.md)\n- [mails.ai Agent Email vs Postfleet](https://www.anchorterminal.com/compare/mails-ai-vs-postfleet.md)\n- [mails.ai Agent Email vs Robotomail](https://www.anchorterminal.com/compare/mails-ai-vs-robotomail.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Clawpost vs mails.ai Agent Email", "url": "" } ], "description": "mails.ai Agent Email scores 65.2 (B) to Clawpost's 36.8 (F) for agent inboxes. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Clawpost F 36.8", "mails.ai Agent Email B 65.2", "scores" ], "h1": "Clawpost vs mails.ai Agent Email", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/clawpost-vs-mails-ai", "published": "2026-10-01", "section": "tools", "title": "Clawpost vs mails.ai Agent Email for AI agents (2026)", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/clawpost-vs-mails-ai" }, "tokens": { "markdown": 5050, "slim": 3330 }, "version": 1 }