Head to head · Agent inboxes · October 2026 research run

Clawpost vs Lumbox

Lumbox scores 60.7 (C) on agent readiness against Clawpost's 36.8 (F), and leads in 6 of 7 scored categories. Clawpost leads on payments & pricing. Both do agent inboxes.

Best email inbox APIs for AI agents · All 66 inboxes comparisons

Which one, for what

Clawpost F

Best for A developer who wants an agent inbox on their own domain and Cloudflare account with a default approval gate.

Ahead on

  • Payments & pricing, 60 against 40

Also in its favour

  • Open source

Watch for

One shared API key grants every REST and MCP operation; no scopes or read-only key

Lumbox C

Best for Agents that need their own address to receive sign-up codes and links and to send replies.

Ahead on

  • Reliability, 45 against 8
  • Schema & documentation, 82 against 54
  • Agent ergonomics, 78 against 53
  • Security & auth, 71 against 42
  • Maintenance & community, 23 against 2
  • Transparency & trust, 72 against 32

Also in its favour

  • A hosted endpoint, with nothing to install
  • Runs on your own machine
  • Free to start without a card

Watch for

No status page, incident history or SLA; the terms say availability isn't guaranteed

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Transparency & trust Lumbox +40

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.

Lumbox 72

A closed hosted service; the security page says it can be self-hosted, but the repository the deployment guide clones isn't publicly readable. The footer names Cyphen Innovations Private Limited (15 of 30). The privacy policy and security page agree that mail is kept while its inbox exists and an account's data is deleted within 30 days, that email isn't used for training, and that the vault uses AES-256-GCM per-organisation keys (26 of 30). A deprecation policy with Deprecation and Sunset headers, 90 days' notice and 12 months for an old version (20). Hosts and locations named, Hetzner in Germany, Neon in the US, Vercel, Cloudflare, AWS SES, Dodo Payments and Steel for browsers (18 of 20). Total 79.

Reliability Lumbox +37

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.

Lumbox 45

Graded with the hosted lines. No status page was found; none is linked from the site or llms.txt, and status.lumbox.co doesn't resolve (0). With no history to read, the incident line takes 5. 120 requests a minute per API key, per IP for unauthenticated routes, with X-RateLimit headers (15). 429 returns retry_after_seconds, the spec gives a backoff schedule and says which statuses not to retry, and Idempotency-Key works on every POST for 24 hours (15). The terms say Lumbox doesn't guarantee uninterrupted service, and no SLA was found (0). The core API carries no beta label; dedicated phone numbers are early access (10). Total 45.

Security & auth Lumbox +29

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.

Lumbox 71

OAuth 2.1 with PKCE, dynamic client registration and five scopes that split reading inboxes, reading mail, sending and domain changes, plus API keys stored as SHA-256 hashes that can be limited to named inboxes (30). Inbox-scoped keys and the read and send split keep one run away from another's codes; Lumbox's built-in agent drafts replies for approval, but the API itself sends at once (16 of 20). The terms tell users to treat bodies as untrusted, and the security page says attachment text is sanitised for prompt injection before it reaches an agent (12 of 15). The privacy policy says API calls are logged with endpoint, time and key prefix for rate limiting and billing; no customer-facing audit log was found (5 of 15). A valid security.txt to security@lumbox.co and a responsible disclosure section; not SOC 2 certified, no bug bounty (8 of 20). Total 71.

Schema & documentation Lumbox +28

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.

Lumbox 82

OpenAPI 3.1 at lumbox.co/openapi.json with 29 operations on 23 paths, all described (25). llms.txt with plan limits, endpoints and the MCP setup (10). Descriptions state what each call does, with notes such as long-poll endpoints being safe to retry; the MCP server card gives one line per tool (15 of 20). Typed parameters with limit and cursor, required fields marked (12 of 15). Shared responses for 400 to 429 and a default error on 28 operations, but errors are a bare error string with no code (12 of 15). Path versioning and a written deprecation policy, but the changelog it refers to wasn't found (8 of 15). Total 82.

Agent ergonomics Lumbox +25

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.

Lumbox 78

18 MCP tools, the 11 to 30 band; OAuth scopes narrow what a grant can do, but no read-only tool subset was found (15 of 25). Cursor pagination with limit and has_more, search, and an SSE stream for new mail (20). Errors are a human-readable message with the HTTP status, plus retry_after_seconds on 429 and written guidance on what to retry (12 of 20). Idempotency-Key on every POST; MCP annotations weren't readable without a session (16 of 20). One POST creates an inbox with a default address; official Node and Python SDKs (15). Total 78.

Maintenance & community Lumbox +21

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.

Lumbox 23

The latest package releases found are lumbox 0.3.1 on npm (19 June 2026) and @lumbox/mcp-server 0.2.2 (12 June 2026), 140 days before this check, the 91 to 180 day band (10). No releases or dated changelog entries in the 90 days from 8 August (0). A closed service with a support address and an X account; no changelog (5 of 15). Not in the official MCP registry (search for lumbox returned nothing on 6 November); Node and Python SDKs exist but haven't changed since June (5 of 15). The MCP server card says 0.2.1 while npm has 0.2.2, and the SDK repository named in npm isn't publicly readable (3 of 10). Total 23.

Score by category

CategoryWeight this runClawpostLumboxEdge
Reliability16%20845Lumbox +37
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.25482Lumbox +28
Agent ergonomics13%16.25378Lumbox +25
Security & auth14%17.54271Lumbox +29
Payments & pricing10%12.56040Clawpost +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.8223Lumbox +21
Transparency & trust7%8.83272Lumbox +40
Negative events≤1500
TotalF 36.8/100C 60.7/100

Facts side by side

FactClawpostLumbox
KindMCP serverHTTP API
VendorFrank HarrisCyphen Innovations Private Limited
Hosted endpointno (local only)https://mcp.lumbox.co/mcp
TransportsStreamable HTTP, HTTPHTTP, Streamable HTTP, stdio
AuthAPI keyOAuth or key
PricingFreeFreemium
x402nono
LicenceMITnone
Tools exposed2118
Read-only variant documentednono
llms.txtnoyes
Last release2026-04-012026-06-19
Terms last updatedno document linked2026-09-07
Privacy policy last updatedno document linked2026-03-16
Customer content may train modelsnot read yetnot found in the text
Terms restrict automated accessnot read yetyes
Terms restrict benchmarkingnot read yetnot found in the text
Terms or service can change without noticenot read yetnot found in the text
Arbitration or class-action waivernot read yetnot found in the text
Popularitynone13 npm/wk

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.

Lumbox

Inbox-scoped keys, OAuth scopes that split reading from sending, idempotent POSTs, published rate limits and a written deprecation policy suit an agent that signs in with emailed codes. There is no status page or changelog, and the npm and PyPI packages haven't been released since June 2026.

Before you call either

Clawpost

  1. Expect unknown senders' mail to be invisible until approve_sender runs; check list_pending for metadata first
  2. Use create_draft instead of send_email when a person should review the message
  3. Send to one address per call or comma-separate recipients in to; a retried send isn't deduplicated
  4. Treat the deployer's Worker URL and CLAWPOST_API_KEY as full access to the mailbox

Lumbox

  1. Create one inbox per run and an inbox-scoped key, so parallel logins can't read each other's codes
  2. Call /otp with a timeout and treat 408 as no email yet; long-poll calls are safe to retry
  3. Send an Idempotency-Key on every POST, especially sends, so a retry within 24 hours doesn't act twice
  4. Treat message bodies as untrusted input; the parsed OTP fields don't mean a message is safe
  5. On 429 wait retry_after_seconds, and don't retry 400, 401, 403 or 404

Questions

Which is better for AI agents, Clawpost or Lumbox?

Lumbox scores 60.7 (C) on agent readiness against Clawpost's 36.8 (F), and leads in 6 of 7 scored categories. Clawpost leads on payments & pricing.

Do Clawpost and Lumbox need an API key?

Clawpost needs an API key. Lumbox takes an API key or an OAuth sign-in.

Can an agent call Clawpost and Lumbox without installing anything?

No hosted endpoint is listed for Clawpost. Lumbox has a hosted endpoint at https://mcp.lumbox.co/mcp.

Are Clawpost and Lumbox open source?

Clawpost is open source (MIT). No open-source release is listed for Lumbox.

Other comparisons with Clawpost or Lumbox

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.