# Fix list: ClickSend SMS API + MCP From Anchor Terminal's listing at https://www.anchorterminal.com/tools/clicksend, the October 2026 research run, assessed 1 October 2026. Grade D, 47.8 out of 100. This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public. For a coding agent working on ClickSend SMS API + MCP: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published. ## 1. Security & auth, 23 out of 100, up to 13.5 more on the total Why it scored 23: HTTP Basic auth with the account username and one API key, and subaccounts get their own keys. The MCP server writes the full request options, the Basic `Authorization` header included, to stderr on every call, and MCP hosts keep stderr in log files (10 of 30). No read-only mode or confirmation before sends. Subaccounts give some separation (5 of 20). Inbound replies and SMS history are untrusted text returned straight to the model, with no injection guidance (0 of 15). SMS history and statistics by API (8 of 15). The security page wouldn't load for us (redirect loop), and the 30 September check found no security.txt (0 of 20). The checklist (https://www.anchorterminal.com/benchmark/#checklist-security): - 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option. - 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions. - 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10. - 0 to 15, audit logs or per-call visibility for the operator. - 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public. Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing. ## 2. Payments & pricing, 30 out of 100, up to 8.8 more on the total Why it scored 30: No x402, MPP or L402 (0). Per-message prices by country and volume tier come from a keyless pricing endpoint, for example US SMS $0.0289 down to $0.0095 plus a $0.0041 carrier fee (20). A trial on signup per the 30 September check, and we couldn't confirm whether it needs a card (10 of 20). A person signs up in a browser (0). The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments): The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/). - 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which. - 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login. - 20, a free tier or trial that doesn't need a card. - 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API). Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied. Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol. ## 3. Schema & documentation, 52 out of 100, up to 7.8 more on the total Why it scored 52: No public OpenAPI spec found. The MCP package bundles an OpenAPI 3.0 file for the six SMS endpoints it exposes and builds typed tool inputs from it (15 of 25). llms.txt exists but lists a handful of pages, and we found no Markdown versions (5 of 10). MCP tool descriptions are the operation summary, such as 'Send SMS', with no when-to-use guidance (5 of 20). Typed inputs generated from the spec (10 of 15). The reference has a status-code table and application codes such as INSUFFICIENT_CREDIT and COUNTRY_NOT_ENABLED (12 of 15). /v3 path and no public changelog (5 of 15). The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema): APIs and MCP servers. - 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool). - 10, llms.txt or Markdown docs served for agents. - 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference. - 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs. - 0 to 15, examples and documented error responses. - 15, versioning and a public changelog. Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference. ## 4. Reliability, 65 out of 100, up to 7 more on the total Why it scored 65: Statuspage at status.clicksend.com with a readable history feed (20). The only incident in the last 90 days was a 6-day delay to EU post from 3 to 9 September, outside SMS and the API (30). No rate limit numbers published (0). The API reference lists 429 and a THROTTLED status, with no Retry-After or backoff guidance (5 of 15). No SLA found (0). REST API v3 is generally available (10). The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability): Hosted APIs, MCP servers, models and platforms. - 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own). - 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so. - 15, rate limits documented with numbers. - 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved. - 10, an SLA published for any paid tier. - 10, the surface agents use is generally available, not beta or preview. Local packages, SDKs, frameworks and stdio MCP servers. - 20, installs from an official package with supported runtimes stated. - 25, a public CI and test suite, passing on the default branch. - 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered). - 15, semver discipline and breaking changes called out in a changelog. - 15, version 1.0 or later, or declared stable. Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors. ## 5. Agent ergonomics, 70 out of 100, up to 4.9 more on the total Why it scored 70: 6 MCP tools, with inputs generated from the spec (20 of 25). Pages with page and limit (15 to 100) and a next_page_url, and SMS history filters by date, which the MCP parses from natural language (20). HTTP and application error codes, though the MCP returns them as plain text (15 of 20). No idempotency key on sends and no tool annotations (0 of 20). SDKs in ten languages, and a send needs only a recipient and a body (15). The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics): - 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries). - 20, pagination, filtering and output-size controls. - 20, actionable, documented error responses, codes and messages an agent can recover from. - 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations. - 15, sensible defaults, few required parameters, and official SDKs in at least two languages. Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs. ## 6. Transparency & trust, 55 out of 100, up to 3.9 more on the total Made of editorial 30, provenance 80. Why it scored 55: Closed service with terms from ClickSend Pty Ltd. The MCP server is MIT (15). The privacy policy was last updated in September 2023, names no retention periods and links a sub-processor page that wouldn't load for us (10 of 30). No deprecation policy found, and the legacy HTTP v2 and SMPP APIs are still documented (0 of 20). Sub-processors linked but unchecked (5 of 20). The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency): - 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms. - 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors). - 0 to 20, a deprecation policy or notices with dates. - 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted). The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two. Provenance checks not met in full (half of this category, computed from checked facts): - Changelog: not found (0 of 10) - security.txt: not found (0 of 10) ## 7. Maintenance & community, 62 out of 100, up to 3.3 more on the total Why it scored 62: clicksend-client 6.0.2 on PyPI on 2026-09-25 (30). That and the MCP package's 2026.8.23 release are the two releases we found in the last 90 days (10 of 20). The MCP repo's 2026 commits only changed its registry name, and there's no public changelog (5 of 15). Official SDKs in ten languages, the Python one current and the Node one last tagged on 2026-05-14 (15). The MCP depends on the deprecated request package and a placeholder http package, and has no CI (2 of 10). The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance): - 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older. - 20, at least three releases or dated changelog entries in the last 90 days. - 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15. - 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models). - 10, package health, current dependencies and CI. Models are read for deprecation notice periods and model churn rather than release counts. ## Deductions Each comes off the total. A fixed and documented problem counts for less at the next check. - Since 2025-05-16 the official MCP server has logged each request's options to stderr, including the Basic `Authorization` header that encodes the username and API key, along with every request and response body. The published 2026.8.23 package was built from that code. The credential stays in local log files rather than leaving the machine, so -3 (https://github.com/ClickSend/clicksend-mcp-server/blob/main/src/helper/clicksend.ts). ## What we couldn't check What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it. - Whether the trial needs a card - ClickSend's security programme and certifications, since its security page loops on redirects - Whether subaccount keys can be limited by permission - Whether Sinch's trust centre certifications cover ClickSend ## Weaknesses - The MCP logs the Basic auth header, which encodes the API key, to stderr on every request - One API key per account or subaccount, with no scopes or read-only mode - No rate limits, Retry-After or idempotency key documented - US SMS at $0.0289 a message on the entry tier, falling to $0.0095 only on the top tier - No public OpenAPI spec or changelog, and the privacy policy dates from September 2023 ## What costs an agent a turn today The notes we give agents before they call it. Each one is a workaround an agent shouldn't need. - Call calculate-sms-price before a bulk send, the pricing endpoint needs no key - Pass the user's own date words in user_date_request when reading SMS history - Use a subaccount key for the agent, not the main account key - Restrict access to the MCP host's log files, they contain the encoded API key - Leave links out of messages, ClickSend pauses SMS with URLs for new customers ## What the review panel asked for - Publish the tier thresholds - Publish rate limits - Add Retry-After ## When it's done Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.