Clawpost vs MailSlurp

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.

MailSlurp 75

Graded as a hosted service, on the REST API. status.mailslurp.com is an updown.io page with eight checks, among them the API, email processes, IMAP and SMTP. It shows one month of uptime per check and has no incident log (14 of 20). All eight checks read 100 per cent for 9 September to 9 October 2026 on the 9 October check and for 1 October to 1 November on 1 November, though the API check's "up since" time of 28 October 06:03 UTC shows a short interruption before it. The page shows nothing older, so 3 August to 9 September couldn't be read and the 90-day record is only partly readable (20 of 30). A guide states a limit of 150 requests a second and the pricing page gives monthly quotas per plan. The errors and limits page in the docs has no numbers (13 of 15). The docs describe retryable, retryAfterSeconds and Retry-After on some 429s, warn that 429 also means a plan or sending restriction, and advise bounded backoff. Agent reply, draft send and SMS send operations take an Idempotency-Key header (14 of 15). An Enterprise page says MailSlurp targets 99 per cent uptime for the core API, and section 9.2 of the terms says no SLA applies without a signed amendment (4 of 10). No beta label on the API or the MCP server, which reported version 1.5.0 on 9 October (10). The limits, SLA and MCP pages are per the 9 October check, not re-read on 1 November.

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.

MailSlurp 55

Official SDK releases 17.6.0 for Python, Java, Go and PHP were tagged on 26 October 2026, each regenerated with code changes, and the listed mailslurp-client for JavaScript on 24 September (30). Since 3 August those are the only dated releases, five SDK tags that count half each (2.5), and there is no public API changelog, so the line for three in 90 days isn't met. The 9 October check met it with v17.3.0 and v17.4.0 of 14 July, which have left the window (0). Closed service with no public API changelog. A support page and a public board for product requests are linked, and we did not test support (6 of 15). The JavaScript, Python, Java, Go and PHP clients are at 17.6.0, while Ruby and C# stay at 17.5.0 from 31 March (13 of 15). The JavaScript client's tests moved to Vitest on 24 September. Its CI status was not read (6 of 10).

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.

MailSlurp 84

Graded on the REST API, with the MCP server noted. Agent lists return previews with size defaulting to 20 and capped at 100, and GET /agent/emails/{emailId}/summary returns a compact message. The MCP docs list 16 tools, whose definitions were not read (20 of 25). page, size, sort, since and before on lists, a search operation per inbox and wait operations with a deadline (20). Agent errors carry code, message, retryable, suggestedAction and requestId. The docs say these fields are not on every failure, and the OpenAPI file documents no error response (15 of 20). Idempotency-Key on ten operations, among them agent replies, draft sends and SMS sends, plus expectedConversationVersion on replies. The standard send operation has none, and MCP annotations were not read (14 of 20). POST /inboxes needs no parameter, and the docs list SDKs for ten languages (15).

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.

MailSlurp 70

MCP OAuth with client registration, and scoped agent keys with five roles and a scope of inbox IDs, tags or the whole account, shown once, with disable and revoke. The account API key is all-powerful and the docs accept it as an ?apiKey= query parameter, so less 10 (20 of 30). AGENT_READ_ONLY and AGENT_DRAFT_ONLY roles, and a review queue where a person sends an agent's draft. Send-capable roles send without confirmation (18 of 20). Inbound mail is untrusted content. The docs and llms.txt tell operators to treat bodies, links and attachments as untrusted, and no technical mitigation is described (9 of 15). An Activity page per agent records action, tool name, inbox, email and outcome, with an activity endpoint for account owners. The pricing page lists account audit logs under Enterprise (13 of 15). A security policy page, a trust centre showing SOC 2 Type 1, and a stated practice of regular penetration tests. No security.txt, no bug bounty and no public advisories were found (10 of 20).

Clawpost 60

Free self-hosted software with nothing to buy from the author, which the rubric scores 20 + 20 + 20. Running it needs the deployer's own Cloudflare Workers Paid plan at $5 a month, which isn't Clawpost's charge. No payment protocol (0 of 40). Total 60.

MailSlurp 32

No x402, MPP or L402 found (0 of 40). Four plan prices are public, with unit rates for extra device renders, placement tests and AI extraction. The phone and SMS rate table was empty in the page we read, and usage billing for inbox creations beyond a plan has no stated rate (15 of 20). A Free plan at $0 with 500 emails received a month. The page does not say whether signup asks for a card, and we did not sign up (17 of 20). A person signs up in a browser and creates the first key in the dashboard. Agent keys can then be created by API with an account key (0 of 20).

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.

MailSlurp 60

Closed service under published terms, with an MIT JavaScript client (17 of 30). One legal document dated 16 January 2026 holds the privacy policy and the DPA. It gives no retention periods and says MailSlurp does not guarantee data retention. Section 7.5.1 promises 14 days' notice of a new sub-processor and section 8.4 says no advance notice is required. The AI disclosure makes no statement on whether AI inputs are kept or used for model improvement by third parties (12 of 30). Nine operations are marked deprecated in the OpenAPI file with no dates, and no deprecation policy was found (4 of 20). The security policy names AWS us-west-2. The trust centre lists four subprocessors and no payment or AI model provider, while the privacy policy names payment processors and analytics providers as recipients (12 of 20).