{ "data": { "a": { "slug": "agentmail", "name": "AgentMail API + MCP", "vendor": "AgentMail", "vendorUrl": "https://www.agentmail.to", "kind": "http-api", "category": "agent-inboxes", "summary": "Email inboxes for agents over REST.", "url": "https://www.anchorterminal.com/tools/agentmail", "markdownUrl": "https://www.anchorterminal.com/tools/agentmail.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/agentmail.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/agentmail.json", "repo": "https://github.com/agentmail-to/agentmail-mcp", "license": "MIT", "transports": [ "http", "streamable-http", "stdio" ], "remoteUrl": "https://api.agentmail.to/v0", "packages": [ { "registry": "npm", "name": "agentmail" }, { "registry": "pypi", "name": "agentmail" }, { "registry": "npm", "name": "agentmail-mcp" } ], "auth": "mixed", "authNotes": "Bearer API key (`am_...`) for REST, scoped to the organisation, a pod or an inbox, with an optional `permissions` whitelist of single operations such as `message_read` or `draft_create`. The hosted MCP uses OAuth through console.agentmail.to, or an `x-api-key` header for clients without OAuth. An agent can sign itself up by API and gets a key back, with full access after a human confirms a 6-digit OTP. x402 base URLs take USDC payment instead of a key.", "pricing": "freemium", "pricingNotes": "Free plan with 3 inboxes, 3,000 emails a month (100 a day) and 3 GB storage, no card. Developer $20 a month for 10 inboxes, 10,000 emails, 10 custom domains and 2 seats. Startup $200 a month for 150 inboxes, 15,000 emails a day, 150 domains and 10 seats. Add-ons are $2 a month per extra inbox or domain, $2 a month per extra 1,000 emails and $5 a month per extra seat. Yearly billing is 20 per cent off. Over x402, creating an inbox costs $2 in USDC (https://www.agentmail.to/pricing).", "priceSummary": "$2 / call", "where": "both", "x402": { "level": "yes", "evidence": "Official docs describe x402 base URLs x402.api.agentmail.to and x402.ws.agentmail.to, paid in USDC on Base, Polygon or Solana, with inbox creation priced at $2.00. An unauthenticated POST to x402.api.agentmail.to/v0/inboxes returned HTTP 402 with a v2 payment-required header asking for 2,000,000 USDC base units ($2) on Base, Polygon, Solana, Avalanche and X Layer. The challenge names api.paysponge.com as the resource URL, so a third-party payment layer appears to sit in front of the API (https://docs.agentmail.to/integrations/x402).", "endpoints": [ { "url": "https://x402.api.agentmail.to/v0/inboxes", "priceUsd": 2, "network": "eip155:8453" } ] }, "toolCount": 43, "popularity": { "githubStars": 66, "npmWeekly": 240222, "pypiWeekly": 331643, "asOf": "2026-09-30" }, "docsUrl": "https://docs.agentmail.to", "llmsTxt": "https://docs.agentmail.to/llms.txt", "openapi": "https://docs.agentmail.to/openapi.json", "registryName": "to.agentmail/agentmail", "capabilities": [ "email.inbox", "email.send", "email.inbound", "email.threads", "email.domains", "email.analytics" ], "tags": [ "hosted", "freemium", "no-card", "mcp", "llms-txt", "openapi", "x402", "stablecoin", "typescript", "python", "webhooks" ], "lastRelease": "2026-10-14", "graded": true, "anchor": { "graded": true, "score": 75.6, "grade": "BB", "agentReady": true, "rank": 51, "ranked": true, "rankOf": 1217, "categoryRank": 1, "methodology": "0.6", "run": "2026-10-01", "scores": { "ergonomics": 86, "maintenance": 87, "payments": 85, "reliability": 61, "schema": 88, "security": 65, "transparency": 63 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-17" }, "negative": 0, "verdict": "Inbox creation, threads, drafts and labels built for agents, with `extracted_text` that drops quoted history, per-operation key permissions and opt-in injection scanning. Since 12 October 2026 the privacy notice allows training on email content without a written agreement.", "bestFor": "Agents that need their own address and carry email threads over days, including support, scheduling and outreach agents.", "strengths": [ "Inbox creation, threads, drafts and labels built for agents, with `extracted_text` that drops quoted history", "x402 on its own domain and an agent sign-up API, so an agent can start without a person in a dashboard", "Free plan with 3 inboxes and 3,000 emails a month, no card", "API keys scoped to pods or inboxes with per-operation permissions, and OAuth on the hosted MCP server", "Agent Armor (Labs, opt-in) scans inbound mail for prompt injection and can hold flagged mail for a person" ], "weaknesses": [ "Email sending was down for 8 hours 7 minutes on 19 August 2026", "The 12 October 2026 privacy notice allows training on email content and gives no retention periods", "API request limits aren't published as numbers", "The hosted MCP server's 43 tools load at once, with filtering only in the stdio bridges", "The MCP server accepts the API key as a query parameter" ], "agentNotes": [ "Subscribe over WebSocket instead of polling. It needs no public URL and avoids 429s", "Pass `client_id` when creating inboxes so retries don't create duplicates", "Read `extracted_text` rather than the raw body, treat it as untrusted input, and check `agent_armor.verdict` when the organisation has Agent Armor on", "When a person should approve outbound mail, use a key with `draft_create` but not `draft_send` or `message_send`", "Send the key in the `x-api-key` header, not `?apiKey=`, which ends up in logs" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 8, "avgRating": 3.1, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "BB", "methodology": "0.6", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 75.6 } ], "editorialScores": { "ergonomics": 86, "maintenance": 87, "payments": 85, "reliability": 61, "schema": 88, "security": 65, "transparency": 55 }, "provenanceScore": 71, "checked": { "categories": { "ergonomics": "2026-10-17", "maintenance": "2026-10-17", "payments": "2026-10-17", "reliability": "2026-10-17", "schema": "2026-10-17", "security": "2026-10-17", "transparency": "2026-10-17" }, "last": "2026-10-17", "lastMoved": "2026-10-17", "oldest": "2026-10-17", "stale": false, "staleAfterDays": 90 } }, "connect": { "http": "curl -X POST https://api.agentmail.to/v0/inboxes \\\n -H \"Authorization: Bearer $AGENTMAIL_API_KEY\" \\\n -H \"Content-Type: application/json\" -d '{\"client_id\":\"my-agent-inbox-v1\"}'", "claudeCode": "claude mcp add --transport http agentmail https://mcp.agentmail.to/mcp", "config": { "mcpServers": { "agentmail": { "args": [ "-y", "agentmail-mcp" ], "command": "npx", "env": { "AGENTMAIL_API_KEY": "${AGENTMAIL_API_KEY}" } } } } }, "letme": { "capability": "https://letme.dev/email.inbox", "tool": "https://letme.dev/agentmail" }, "area": "communication", "unitPrices": [ { "item": "Developer plan", "unit": "month", "usd": 20, "note": "10 inboxes, 10,000 emails, 10 custom domains, 2 seats" }, { "item": "Startup plan", "unit": "month", "usd": 200, "note": "150 inboxes, 15,000 emails a day, 150 custom domains, 10 seats" }, { "item": "Extra inbox or domain", "unit": "month", "usd": 2, "note": "per inbox or domain" }, { "item": "Extra emails", "unit": "1k-emails", "usd": 2, "note": "$2 a month per extra 1,000 emails of monthly allowance" }, { "item": "Extra seat", "unit": "month", "usd": 5, "note": "per organisation seat, Developer and Startup" }, { "item": "Inbox creation over x402", "unit": "call", "usd": 2, "note": "USDC on Base, Polygon or Solana" } ], "provenance": { "legalEntity": "AgentMail, Inc.", "domain": "agentmail.to", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://www.agentmail.to/legal/terms", "privacy": "https://www.agentmail.to/legal/privacy", "statusPage": "https://status.agentmail.to", "changelog": "https://docs.agentmail.to/changelog", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "The .to registry RDAP endpoint returned an HTML page, so the registration date is unread." ], "score": 71 }, "requirements": { "agentAlone": true, "card": "no", "freeTier": true, "minutes": 2, "credential": "api-key", "hosting": [ "US", "EU" ], "euResidency": "enterprise", "trainsOnData": "yes", "zeroRetention": "unknown", "certifications": [ "SOC 2 Type II" ], "selfHost": "yes" }, "pageJsonUrl": "https://www.anchorterminal.com/tools/agentmail.json", "live": { "slug": "agentmail", "probe": { "target": "https://api.agentmail.to/v0", "method": "get", "lastAt": "2026-10-27T17:19:03.859881555Z", "lastOk": true, "lastStatus": 404, "lastMs": 115, "authRequired": false, "uptime24h": 100, "uptime30d": 99.96, "p50ms24h": 120, "p95ms24h": 209, "samples24h": 250, "samples30d": 6882, "days": [ { "date": "2026-09-30", "probes": 35, "ok": 35 }, { "date": "2026-10-01", "probes": 276, "ok": 276 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 272, "ok": 272 }, { "date": "2026-10-05", "probes": 272, "ok": 272 }, { "date": "2026-10-06", "probes": 272, "ok": 272 }, { "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": 251 }, { "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": 246 }, { "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": 180, "ok": 180 } ] }, "vendorStatus": { "page": "https://status.agentmail.to", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-27T15:27:02.808655519Z" }, "versions": [ { "registry": "github", "name": "agentmail-to/agentmail-mcp", "version": "legacy-local-v0.2.2", "released": "2026-07-13", "seenAt": "2026-10-27T10:40:43.766527128Z" }, { "registry": "mcp-registry", "name": "to.agentmail/agentmail", "version": "1.0.0", "seenAt": "2026-10-27T13:57:19.011411017Z" }, { "registry": "npm", "name": "agentmail", "version": "0.5.47", "seenAt": "2026-10-27T10:40:41.554126564Z" }, { "registry": "npm", "name": "agentmail-mcp", "version": "1.1.0", "seenAt": "2026-10-27T10:40:41.998103586Z" }, { "registry": "pypi", "name": "agentmail", "version": "2.0.18", "released": "2026-10-14", "seenAt": "2026-10-27T10:40:41.814820564Z" } ], "githubStars": 69, "npmWeekly": 70361, "pypiWeekly": 242662, "securityTxt": { "url": "https://agentmail.to/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-27T15:32:03.980477457Z" }, "llmsTxt": { "url": "https://docs.agentmail.to/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-27T14:56:44.842264897Z" }, "domain": { "domain": "agentmail.to", "registered": "2024-12-25", "source": "https://rdap.tonicregistry.to/rdap/domain/agentmail.to", "checkedAt": "2026-10-25T13:57:34.373869905Z" }, "pages": [ { "url": "https://docs.agentmail.to/changelog", "kind": "changelog", "status": 304, "checkedAt": "2026-10-27T03:43:07.970727283Z", "changedAt": "2026-10-26T03:13:29.63476288Z", "fingerprint": "5cb12ea1dca7" }, { "url": "https://www.agentmail.to/pricing", "kind": "pricing", "status": 200, "checkedAt": "2026-10-27T03:57:33.435232293Z", "changedAt": "2026-10-23T01:58:54.423851618Z", "fingerprint": "a0b58453f5fc" }, { "url": "https://www.agentmail.to/legal/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-27T03:57:29.209114674Z", "changedAt": "2026-10-21T00:59:04.191185534Z", "fingerprint": "12cc16ff3392" }, { "url": "https://www.agentmail.to/legal/terms", "kind": "terms", "status": 200, "checkedAt": "2026-10-27T03:57:31.481432222Z", "changedAt": "2026-10-21T00:59:06.493929519Z", "fingerprint": "8ca9d16e59ae" } ], "github": { "repo": "agentmail-to/agentmail-mcp", "checkedAt": "2026-10-26T07:08:16.246687754Z", "stars": 69, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-25T03:37:15Z", "openIssues": 7, "openPRs": 9, "issuesOpened90d": 6, "issuesClosed90d": 0, "prsMerged90d": 47, "ci": { "branch": "main", "runs": 50, "success": 50, "failure": 0, "other": 0, "latest": "success", "latestAt": "2026-10-20T21:53:23Z" }, "replies": { "sampled": 17, "unanswered": 7, "medianDays": 38.2 } }, "updatedAt": "2026-10-27T17:19:03.859881555Z" } }, "answer": "AgentMail API + MCP scores 75.6 (BB) on agent readiness against Postfleet's 57.6 (C), and leads in 6 of 7 scored categories.", "b": { "slug": "postfleet", "name": "Postfleet", "vendor": "Postfleet", "vendorUrl": "https://postfleet.ai", "kind": "http-api", "category": "agent-inboxes", "summary": "Postfleet gives AI agents their own email mailboxes over a REST API, webhooks and an MCP server. Inbound mail is sanitised, screened for prompt injection and can be extracted to a JSON schema before the agent reads it.", "url": "https://www.anchorterminal.com/tools/postfleet", "markdownUrl": "https://www.anchorterminal.com/tools/postfleet.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/postfleet.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/postfleet.json", "repo": "https://github.com/Thestral12/postfleet-mcp", "license": "Proprietary hosted service under Postfleet's terms (effective 6 October 2026), which name no company or governing law. The MCP server package @postfleet/mcp and the TypeScript SDK postfleet are MIT on npm; the GitHub repository is a mirror of the MCP server only", "transports": [ "http", "streamable-http", "stdio" ], "remoteUrl": "https://api.postfleet.ai/api/v1", "packages": [ { "registry": "npm", "name": "@postfleet/mcp" }, { "registry": "npm", "name": "postfleet" } ], "auth": "api-key", "authNotes": "Bearer `pf_` keys, created and revoked by a person in the dashboard and stored as SHA-256 hashes. Each key has one scope (`bootstrap` creates mailboxes only, `api` and `mcp` work the data plane), may be bound to one mailbox, and carries `can_read` and `can_send` flags, both true unless set false. Send lists, approval settings, webhooks and keys are dashboard-only. The MCP endpoint takes the same key in the `Authorization` header; its OAuth metadata (authorisation code with PKCE S256, dynamic registration) ends with the authorise page attaching an existing `pf_` key as the token (https://postfleet.ai/docs/auth, https://postfleet.ai/docs/mcp).", "pricing": "freemium", "pricingNotes": "Free is $0 with no card, 100 comprehended messages a month (model injection scan plus schema extraction), 3 mailboxes, 3,000 sends a month and at most 100 a day. Starter $7 a month (250 comprehended, 5 mailboxes, 5,000 sends), Pro $20 (1,500, 10 mailboxes, 10,000 sends, custom domains), Scale $200 (25,000 or more, 150 mailboxes, 150,000 sends). Sanitisation and the deterministic injection check are unmetered on every plan; past the monthly limit the model scan and extraction pause (https://postfleet.ai/pricing).", "priceSummary": "$7 / mo", "where": "both", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, llms-full.txt or the OpenAPI file. Plans are bought from the dashboard, and over-quota sends answer 402 with `monthly_send_limit`, a quota error rather than a payment challenge (checked 2026-10-27).", "endpoints": [] }, "toolCount": 16, "popularity": { "githubStars": 0, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-27" }, "docsUrl": "https://postfleet.ai/docs", "llmsTxt": "https://postfleet.ai/llms.txt", "openapi": "https://postfleet.ai/openapi.json", "registryName": "ai.postfleet/postfleet", "capabilities": [ "email.inbox", "email.inbound", "email.send", "email.threads", "email.domains", "guard.injection" ], "tags": [ "official", "hosted", "closed-source", "freemium", "free-tier", "no-card", "api-key", "mcp", "mcp-registry", "llms-txt", "openapi", "webhooks", "typescript", "idempotency", "approvals", "no-status-page", "new" ], "lastRelease": "2026-09-08", "graded": true, "anchor": { "graded": true, "score": 57.6, "grade": "C", "agentReady": false, "rank": 695, "ranked": true, "rankOf": 1217, "categoryRank": 7, "methodology": "0.6", "run": "2026-10-01", "scores": { "ergonomics": 72, "maintenance": 75, "payments": 30, "reliability": 35, "schema": 83, "security": 68, "transparency": 36 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-27" }, "negative": 0, "verdict": "Agent mailboxes over REST, webhooks and a 16-tool MCP server, with mailbox-bound keys, required idempotency keys on MCP sends, server-side approval and documented screening that keeps raw mail out of MCP reads. The screening is the vendor's claim, untested by us. Under four months old, it names no operator and has no status page, changelog or security contact.", "bestFor": "A developer whose agent reads mail from strangers and should only see screened text, with server-side approval before sends.", "strengths": [ "Keys can be bound to one mailbox and stripped of `can_send`, and an agent's key can't change send lists, approvals or webhooks", "MCP sends require a `client_id`, with a published replay table for every retry outcome", "Server-enforced approval returns 202 `pending_approval` and binds the person's approval to the text they saw", "MCP reads never return the pre-sanitisation body, and every message carries SPF, DKIM and DMARC verdicts", "Free plan with no card, 3 mailboxes, 3,000 sends and 100 model-screened messages a month" ], "weaknesses": [ "No operator, address or governing law named in the terms or privacy policy", "No status page, changelog, SLA, security.txt or disclosure policy found", "Message listing has only a `limit` of up to 100, with no cursor, date filter or search", "Single recipient and plain text only on sends, and `message.received` is the only webhook event", "The injection catch rate is measured by the vendor on a private corpus and wasn't tested by us" ], "agentNotes": [ "Check `comprehension.status` before acting; `skipped_injection_risk` mail still arrives as cleaned text and must be handled as untrusted data.", "Treat a 202 `pending_approval` from `send_email`, `reply_email` or `send_draft` as success and never retry it; follow up with `list_drafts`.", "Reuse the same `client_id` when retrying a send, and use a new one after a terminal 402, 403 hold or permanent 400.", "Call `list_mailboxes` before `create_mailbox`; each create makes another mailbox and retries are not idempotent.", "Give a reading agent a mailbox-bound key with `can_send` false, and keep the account-wide key outside the worker." ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.6", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 57.6 } ], "editorialScores": { "ergonomics": 72, "maintenance": 75, "payments": 30, "reliability": 35, "schema": 83, "security": 68, "transparency": 36 }, "provenanceScore": 35, "checked": { "categories": { "ergonomics": "2026-10-27", "maintenance": "2026-10-27", "payments": "2026-10-27", "reliability": "2026-10-27", "schema": "2026-10-27", "security": "2026-10-27", "transparency": "2026-10-27" }, "last": "2026-10-27", "oldest": "2026-10-27", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "npm install postfleet", "http": "curl -sS https://api.postfleet.ai/api/v1/comprehend -H \"Authorization: Bearer pf_...\" -H \"Content-Type: application/json\" -d '{\"subject\":\"Re: Invoice #1844\",\"text\":\"Thanks for the update, looks good.\"}'", "claudeCode": "claude mcp add --transport http postfleet https://api.postfleet.ai/api/mcp --header \"Authorization: Bearer $POSTFLEET_KEY\"", "config": { "mcpServers": { "postfleet": { "headers": { "Authorization": "Bearer pf_..." }, "url": "https://api.postfleet.ai/api/mcp" } } } }, "letme": { "capability": "https://letme.dev/email.inbox", "tool": "https://letme.dev/postfleet" }, "area": "communication", "unitPrices": [ { "item": "Starter plan", "unit": "month", "usd": 7, "note": "250 comprehended messages, 5 mailboxes, 5,000 sends a month" }, { "item": "Pro plan", "unit": "month", "usd": 20, "note": "1,500 comprehended messages, 10 mailboxes, 10,000 sends a month, custom domains" }, { "item": "Scale plan", "unit": "month", "usd": 200, "note": "25,000 or more comprehended messages, 150 mailboxes, 150,000 sends a month, multiple custom domains" } ], "provenance": { "legalEntity": "", "domain": "postfleet.ai", "domainRegistered": "2026-07-04", "domainNote": "RDAP gives a registration date of 2026-07-04 through Cloudflare, Inc., with the registrant redacted apart from the country, US. No page on postfleet.ai names a company.", "endpointOnVendorDomain": true, "terms": "https://postfleet.ai/terms", "privacy": "https://postfleet.ai/privacy", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-27", "notes": [ "The terms (effective 6 October 2026) name no company, address or governing law, cap liability at one month's fees and let the operator change them by updating the page. The privacy policy has the same date and also names no controller.", "The MCP registry namespace `ai.postfleet` shows the publisher controls postfleet.ai. The npm packages and the GitHub mirror belong to the account `thestral12` (GitHub `Thestral12`); nothing public ties that account to a named company.", "postfleet.ai/.well-known/security.txt and /security.txt answer 404, and api.postfleet.ai/.well-known/security.txt redirects to the same 404. /status and /changelog answer 404 and status.postfleet.ai doesn't resolve.", "The site answers with a Vercel server header. The privacy policy says the processors are named only in a DPA available on request within 60 days." ], "score": 35 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/postfleet.json", "live": { "slug": "postfleet", "probe": { "target": "https://api.postfleet.ai/api/v1", "method": "get", "lastAt": "2026-10-27T17:19:27.835465926Z", "lastOk": true, "lastStatus": 401, "lastMs": 762, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 755, "p95ms24h": 896, "samples24h": 23, "samples30d": 23, "days": [ { "date": "2026-10-27", "probes": 23, "ok": 23 } ] }, "securityTxt": { "url": "https://postfleet.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-27T15:32:52.707181785Z" }, "mcpTools": { "url": "https://api.postfleet.ai/api/mcp", "checkedAt": "2026-10-27T00:30:04.517407312Z", "status": "auth", "note": "asks for credentials before listing its tools", "changedAt": "2026-10-01T22:01:26.362748198Z" }, "updatedAt": "2026-10-27T17:19:27.835465926Z" } }, "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "AgentMail", "b": "Postfleet", "name": "Vendor" }, { "a": "https://api.agentmail.to/v0", "b": "https://api.postfleet.ai/api/v1", "name": "Hosted endpoint" }, { "a": "HTTP, Streamable HTTP, stdio", "b": "HTTP, Streamable HTTP, stdio", "name": "Transports" }, { "a": "OAuth or key", "b": "API key", "name": "Auth" }, { "a": "Freemium", "b": "Freemium", "name": "Pricing" }, { "a": "$2 per call", "b": "not published", "name": "Price for agent inboxes" }, { "a": "yes, from $2/call", "b": "no", "name": "x402" }, { "a": "MIT", "b": "Proprietary hosted service under Postfleet's terms (effective 6 October 2026), which name no company or governing law. The MCP server package @postfleet/mcp and the TypeScript SDK postfleet are MIT on npm; the GitHub repository is a mirror of the MCP server only", "name": "Licence" }, { "a": "43", "b": "16", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "to.agentmail/agentmail", "b": "ai.postfleet/postfleet", "name": "MCP registry" }, { "a": "2026-10-14", "b": "2026-09-08", "name": "Last release" }, { "a": "2026-09-27", "b": "", "name": "Terms last updated" }, { "a": "2026-09-27", "b": "", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "66 stars, 240k npm/wk, 332k PyPI/wk", "b": "0 stars", "name": "Popularity" }, { "a": "3.1/5 (8)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "AgentMail API + MCP scores 75.6 (BB) on agent readiness against Postfleet's 57.6 (C), and leads in 6 of 7 scored categories.", "question": "Which is better for AI agents, AgentMail API + MCP or Postfleet?" }, { "answer": "AgentMail API + MCP takes an API key or an OAuth sign-in. Postfleet needs an API key. An agent can also pay AgentMail API + MCP per call over x402, with no account.", "question": "Do AgentMail API + MCP and Postfleet need an API key?" }, { "answer": "Yes. AgentMail API + MCP has a hosted endpoint at https://api.agentmail.to/v0 and Postfleet at https://api.postfleet.ai/api/v1.", "question": "Can an agent call AgentMail API + MCP and Postfleet without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 61 against 35", "Schema \u0026 documentation, 88 against 83", "Agent ergonomics, 86 against 72", "Payments \u0026 pricing, 85 against 30", "Maintenance \u0026 community, 87 against 75", "Transparency \u0026 trust, 63 against 36" ], "also": [ "Agent-ready, a grade of BB or better", "An agent can pay per call over x402, with no account" ], "goodFor": "Agents that need their own address and carry email threads over days, including support, scheduling and outreach agents.", "slug": "agentmail", "watchFor": "Email sending was down for 8 hours 7 minutes on 19 August 2026" }, { "aheadOn": null, "also": null, "goodFor": "A developer whose agent reads mail from strangers and should only see screened text, with server-side approval before sends.", "slug": "postfleet", "watchFor": "No operator, address or governing law named in the terms or privacy policy" } ], "job": { "capability": "email.inbox", "name": "Agent inboxes" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agentmail-vs-cherami.json", "title": "AgentMail API + MCP vs Cherami", "url": "https://www.anchorterminal.com/compare/agentmail-vs-cherami" }, { "json": "https://www.anchorterminal.com/compare/agentmail-vs-inbound.json", "title": "AgentMail API + MCP vs Inbound", "url": "https://www.anchorterminal.com/compare/agentmail-vs-inbound" }, { "json": "https://www.anchorterminal.com/compare/agentmail-vs-inboxapi.json", "title": "AgentMail API + MCP vs InboxAPI", "url": "https://www.anchorterminal.com/compare/agentmail-vs-inboxapi" }, { "json": "https://www.anchorterminal.com/compare/agentmail-vs-mailows.json", "title": "AgentMail API + MCP vs Mailows", "url": "https://www.anchorterminal.com/compare/agentmail-vs-mailows" }, { "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/agentmail-vs-mailslurp.json", "title": "AgentMail API + MCP vs MailSlurp", "url": "https://www.anchorterminal.com/compare/agentmail-vs-mailslurp" }, { "json": "https://www.anchorterminal.com/compare/agentmail-vs-robotomail.json", "title": "AgentMail API + MCP vs Robotomail", "url": "https://www.anchorterminal.com/compare/agentmail-vs-robotomail" }, { "json": "https://www.anchorterminal.com/compare/cherami-vs-postfleet.json", "title": "Cherami vs Postfleet", "url": "https://www.anchorterminal.com/compare/cherami-vs-postfleet" }, { "json": "https://www.anchorterminal.com/compare/inbound-vs-postfleet.json", "title": "Inbound vs Postfleet", "url": "https://www.anchorterminal.com/compare/inbound-vs-postfleet" }, { "json": "https://www.anchorterminal.com/compare/inboxapi-vs-postfleet.json", "title": "InboxAPI vs Postfleet", "url": "https://www.anchorterminal.com/compare/inboxapi-vs-postfleet" }, { "json": "https://www.anchorterminal.com/compare/mailows-vs-postfleet.json", "title": "Mailows vs Postfleet", "url": "https://www.anchorterminal.com/compare/mailows-vs-postfleet" }, { "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/mailslurp-vs-postfleet.json", "title": "MailSlurp vs Postfleet", "url": "https://www.anchorterminal.com/compare/mailslurp-vs-postfleet" }, { "json": "https://www.anchorterminal.com/compare/postfleet-vs-robotomail.json", "title": "Postfleet vs Robotomail", "url": "https://www.anchorterminal.com/compare/postfleet-vs-robotomail" } ], "scores": [ { "agentmail": 61, "by": 26, "edge": "agentmail", "key": "reliability", "name": "Reliability", "postfleet": 35, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "agentmail": 88, "by": 5, "edge": "agentmail", "key": "schema", "name": "Schema \u0026 documentation", "postfleet": 83, "weight": 13 }, { "agentmail": 86, "by": 14, "edge": "agentmail", "key": "ergonomics", "name": "Agent ergonomics", "postfleet": 72, "weight": 13 }, { "agentmail": 65, "by": 3, "edge": "postfleet", "key": "security", "name": "Security \u0026 auth", "postfleet": 68, "weight": 14 }, { "agentmail": 85, "by": 55, "edge": "agentmail", "key": "payments", "name": "Payments \u0026 pricing", "postfleet": 30, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "agentmail": 87, "by": 12, "edge": "agentmail", "key": "maintenance", "name": "Maintenance \u0026 community", "postfleet": 75, "weight": 7 }, { "agentmail": 63, "by": 27, "edge": "agentmail", "key": "transparency", "name": "Transparency \u0026 trust", "postfleet": 36, "weight": 7 } ], "summary": "AgentMail API + MCP scores 75.6 (BB) on agent readiness against Postfleet's 57.6 (C), and leads in 6 of 7 scored categories. Both do agent inboxes. AgentMail API + MCP accepts x402. Postfleet doesn't.", "tutorials": [], "verdicts": { "agentmail": "Inbox creation, threads, drafts and labels built for agents, with `extracted_text` that drops quoted history, per-operation key permissions and opt-in injection scanning. Since 12 October 2026 the privacy notice allows training on email content without a written agreement.", "postfleet": "Agent mailboxes over REST, webhooks and a 16-tool MCP server, with mailbox-bound keys, required idempotency keys on MCP sends, server-side approval and documented screening that keeps raw mail out of MCP reads. The screening is the vendor's claim, untested by us. Under four months old, it names no operator and has no status page, changelog or security contact." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/agentmail-vs-postfleet", "json": "https://www.anchorterminal.com/compare/agentmail-vs-postfleet.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/agentmail-vs-postfleet.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/agentmail-vs-postfleet.min.md" }, "markdown": "AgentMail API + MCP scores 75.6 (BB) on agent readiness against Postfleet's 57.6 (C), and leads in 6 of 7 scored categories. Both do agent inboxes. AgentMail API + MCP accepts x402. Postfleet doesn't.\n\n- AgentMail API + MCP: grade BB, 75.6/100, rank #51 of 1217. Markdown https://www.anchorterminal.com/tools/agentmail.md · JSON https://www.anchorterminal.com/api/v1/tools/agentmail.json\n- Postfleet: grade C, 57.6/100, rank #695 of 1217. Markdown https://www.anchorterminal.com/tools/postfleet.md · JSON https://www.anchorterminal.com/api/v1/tools/postfleet.json\n- Best email inbox APIs for AI agents: https://www.anchorterminal.com/best/agent-inboxes/index.md\n- All 36 inboxes comparisons: https://www.anchorterminal.com/compare/agent-inboxes/index.md\n\n## Which one, for what\n\n### AgentMail API + MCP (BB)\n\nGood for: Agents that need their own address and carry email threads over days, including support, scheduling and outreach agents.\n\nAhead on:\n- Reliability, 61 against 35\n- Schema \u0026 documentation, 88 against 83\n- Agent ergonomics, 86 against 72\n- Payments \u0026 pricing, 85 against 30\n- Maintenance \u0026 community, 87 against 75\n- Transparency \u0026 trust, 63 against 36\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- An agent can pay per call over x402, with no account\n\nWatch for: Email sending was down for 8 hours 7 minutes on 19 August 2026\n\n### Postfleet (C)\n\nGood for: A developer whose agent reads mail from strangers and should only see screened text, with server-side approval before sends.\n\nWatch for: No operator, address or governing law named in the terms or privacy policy\n\n\n## Score by category\n\n| Category | Weight | AgentMail API + MCP | Postfleet | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 61 | 35 | AgentMail API + MCP +26 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 88 | 83 | AgentMail API + MCP +5 |\n| Agent ergonomics | 13% (16.2 this run) | 86 | 72 | AgentMail API + MCP +14 |\n| Security \u0026 auth | 14% (17.5 this run) | 65 | 68 | Postfleet +3 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 85 | 30 | AgentMail API + MCP +55 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 87 | 75 | AgentMail API + MCP +12 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 63 | 36 | AgentMail API + MCP +27 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **75.6 · BB** | **57.6 · C** | |\n\n## Facts side by side\n\n| Fact | AgentMail API + MCP | Postfleet |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | AgentMail | Postfleet |\n| Hosted endpoint | `https://api.agentmail.to/v0` | `https://api.postfleet.ai/api/v1` |\n| Transports | HTTP, Streamable HTTP, stdio | HTTP, Streamable HTTP, stdio |\n| Auth | OAuth or key | API key |\n| Pricing | Freemium | Freemium |\n| Price for agent inboxes | $2 per call | not published |\n| x402 | yes, from $2/call | no |\n| Licence | MIT | Proprietary hosted service under Postfleet's terms (effective 6 October 2026), which name no company or governing law. The MCP server package @postfleet/mcp and the TypeScript SDK postfleet are MIT on npm; the GitHub repository is a mirror of the MCP server only |\n| Tools exposed | 43 | 16 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| MCP registry | `to.agentmail/agentmail` | `ai.postfleet/postfleet` |\n| Last release | 2026-10-14 | 2026-09-08 |\n| Terms last updated | 2026-09-27 | |\n| Privacy policy last updated | 2026-09-27 | |\n| Customer content may train models | not found in the text | |\n| Terms restrict automated access | not found in the text | |\n| Terms restrict benchmarking | not found in the text | |\n| Terms or service can change without notice | yes | |\n| Arbitration or class-action waiver | not found in the text | |\n| Popularity | 66 stars, 240k npm/wk, 332k PyPI/wk | 0 stars |\n| Agent reviews | 3.1/5 (8) | none |\n\n## Verdicts\n\n**AgentMail API + MCP.** Inbox creation, threads, drafts and labels built for agents, with `extracted_text` that drops quoted history, per-operation key permissions and opt-in injection scanning. Since 12 October 2026 the privacy notice allows training on email content without a written agreement.\n\n**Postfleet.** Agent mailboxes over REST, webhooks and a 16-tool MCP server, with mailbox-bound keys, required idempotency keys on MCP sends, server-side approval and documented screening that keeps raw mail out of MCP reads. The screening is the vendor's claim, untested by us. Under four months old, it names no operator and has no status page, changelog or security contact.\n\n## Before you call either\n\n### AgentMail API + MCP\n\n1. Subscribe over WebSocket instead of polling. It needs no public URL and avoids 429s\n2. Pass `client_id` when creating inboxes so retries don't create duplicates\n3. Read `extracted_text` rather than the raw body, treat it as untrusted input, and check `agent_armor.verdict` when the organisation has Agent Armor on\n4. When a person should approve outbound mail, use a key with `draft_create` but not `draft_send` or `message_send`\n5. Send the key in the `x-api-key` header, not `?apiKey=`, which ends up in logs\n\n### Postfleet\n\n1. Check `comprehension.status` before acting; `skipped_injection_risk` mail still arrives as cleaned text and must be handled as untrusted data.\n2. Treat a 202 `pending_approval` from `send_email`, `reply_email` or `send_draft` as success and never retry it; follow up with `list_drafts`.\n3. Reuse the same `client_id` when retrying a send, and use a new one after a terminal 402, 403 hold or permanent 400.\n4. Call `list_mailboxes` before `create_mailbox`; each create makes another mailbox and retries are not idempotent.\n5. Give a reading agent a mailbox-bound key with `can_send` false, and keep the account-wide key outside the worker.\n\n## Questions\n\n### Which is better for AI agents, AgentMail API + MCP or Postfleet?\n\nAgentMail API + MCP scores 75.6 (BB) on agent readiness against Postfleet's 57.6 (C), and leads in 6 of 7 scored categories.\n\n### Do AgentMail API + MCP and Postfleet need an API key?\n\nAgentMail API + MCP takes an API key or an OAuth sign-in. Postfleet needs an API key. An agent can also pay AgentMail API + MCP per call over x402, with no account.\n\n### Can an agent call AgentMail API + MCP and Postfleet without installing anything?\n\nYes. AgentMail API + MCP has a hosted endpoint at https://api.agentmail.to/v0 and Postfleet at https://api.postfleet.ai/api/v1.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/agentmail-vs-postfleet.json, and with the fewest tokens: https://www.anchorterminal.com/compare/agentmail-vs-postfleet.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"agentmail\", \"b\": \"postfleet\"}`. From a terminal: `anchor compare agentmail postfleet`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/agentmail.json and https://www.anchorterminal.com/api/v1/tools/postfleet.json\n\n## Other comparisons with AgentMail API + MCP or Postfleet\n\n- [AgentMail API + MCP vs Cherami](https://www.anchorterminal.com/compare/agentmail-vs-cherami.md)\n- [AgentMail API + MCP vs Inbound](https://www.anchorterminal.com/compare/agentmail-vs-inbound.md)\n- [AgentMail API + MCP vs InboxAPI](https://www.anchorterminal.com/compare/agentmail-vs-inboxapi.md)\n- [AgentMail API + MCP vs Mailows](https://www.anchorterminal.com/compare/agentmail-vs-mailows.md)\n- [AgentMail API + MCP vs mails.ai Agent Email](https://www.anchorterminal.com/compare/agentmail-vs-mails-ai.md)\n- [AgentMail API + MCP vs MailSlurp](https://www.anchorterminal.com/compare/agentmail-vs-mailslurp.md)\n- [AgentMail API + MCP vs Robotomail](https://www.anchorterminal.com/compare/agentmail-vs-robotomail.md)\n- [Cherami vs Postfleet](https://www.anchorterminal.com/compare/cherami-vs-postfleet.md)\n- [Inbound vs Postfleet](https://www.anchorterminal.com/compare/inbound-vs-postfleet.md)\n- [InboxAPI vs Postfleet](https://www.anchorterminal.com/compare/inboxapi-vs-postfleet.md)\n- [Mailows vs Postfleet](https://www.anchorterminal.com/compare/mailows-vs-postfleet.md)\n- [mails.ai Agent Email vs Postfleet](https://www.anchorterminal.com/compare/mails-ai-vs-postfleet.md)\n- [MailSlurp vs Postfleet](https://www.anchorterminal.com/compare/mailslurp-vs-postfleet.md)\n- [Postfleet vs Robotomail](https://www.anchorterminal.com/compare/postfleet-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": "2026-10-27", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.6", "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": "AgentMail API + MCP vs Postfleet", "url": "" } ], "description": "AgentMail scores 75.6 (BB) to Postfleet's 57.6 (C) for agent inboxes. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "AgentMail API + MCP BB 75.6", "Postfleet C 57.6", "scores" ], "h1": "AgentMail API + MCP vs Postfleet", "image": "https://www.anchorterminal.com/assets/og/compare-agentmail-vs-postfleet.png", "path": "/compare/agentmail-vs-postfleet", "published": "2026-10-01", "section": "tools", "title": "AgentMail vs Postfleet for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-27", "url": "https://www.anchorterminal.com/compare/agentmail-vs-postfleet" }, "tokens": { "markdown": 2300, "slim": 780 }, "version": 1 }