# Fix list: Templated API + MCP From Anchor Terminal's listing at https://www.anchorterminal.com/tools/templated, the October 2026 research run, assessed 1 October 2026. Grade C, 61.3 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 Templated 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, 38 out of 100, up to 10.9 more on the total Why it scored 38: The REST key has full account access by the docs' own words, and the privacy policy says it can be regenerated. The hosted MCP is an OAuth 2.1 resource server since MCP 1.6.0 (18). The MCP docs offer ?apiKey= in the server URL for automations, less 10 (8). Folder and external ID scoping is enforced server side, and destructive tools are annotated so clients can ask first. No read-only key (12). Tool results pass through allowlists, and the docs describe server-side scoping as a guard against prompt injection (12). No audit log or per-call log found beyond the render list (3). No security.txt (404), no certification or bug bounty. 2FA added in September 2026 (3). 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, 35 out of 100, up to 8.1 more on the total Why it scored 35: No x402, MPP or L402 in the docs or llms-full.txt (0). Plan prices and per-unit credit rules are public in pricing.md, 1 credit an image or PDF page and a pixel-rate formula for video (15). Trial of 50 credits with no card (20). A person signs up in a browser for a key or an OAuth login (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. Agent ergonomics, 63 out of 100, up to 6 more on the total Why it scored 63: 25 MCP tools (15), plus results passed through field allowlists that strip internal ids and billing state before they reach the model (3). Lists take page and limit, default 25, and the MCP can filter to one folder or external ID (17). The API docs document no error codes or bodies. MCP 1.7.1 rewrote billing errors in neutral terms (5). Every tool carries readOnlyHint and destructiveHint, with deletes and template updates marked destructive. No idempotency key (15). Only `template` is required and renders are synchronous by default, but there are no official SDKs, only code samples in JavaScript, Python and PHP (8). 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. ## 4. Reliability, 75 out of 100, up to 5 more on the total Why it scored 75: Better Stack status page with API, App and Website components over 30, 60 and 90 days (20). No incidents posted, and the page's own figure for the API is 99.998 per cent (30). Rate limits per plan in the Markdown price list, 60, 150 and 300 requests a minute (15). No 429 behaviour, Retry-After or retry advice in the API docs or llms-full.txt (0). No SLA found on the pricing page (0). The render API is GA. Video was announced as beta on 7 January 2026 and we didn't find a later GA note (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. Schema & documentation, 72 out of 100, up to 4.6 more on the total Why it scored 72: No OpenAPI. All 25 MCP tools carry typed JSON Schema inputs, and server.json is published to the MCP registry, so partial credit (18). llms.txt, llms-small.txt, llms-full.txt and pricing.md (10). Some MCP descriptions guide the model well (update_template explains pages versus layers), others are one line, such as 'List all renders in the account' (12). Format and layer type enums and a required template field, but size, scale and fps limits sit in prose rather than min and max, and `layers` is an open object (10). Request and response examples per endpoint, no documented error responses (7). Versioned /v1 path, a dated changelog and tagged MCP releases (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. ## 6. Transparency & trust, 72 out of 100, up to 2.5 more on the total Made of editorial 61, provenance 82. Why it scored 72: MCP server MIT with a `LICENSE` file. The rendering service is closed under published terms (18). Privacy policy updated 8 September 2026 with retention stated per data type (until you delete, files purged within 90 days of deletion, logs up to 90 days, billing records five years) and a DPA at templated.io/dpa, though it doesn't say whether customer content trains models (25). No deprecation policy or dated deprecation notices found (0). Subprocessors named by purpose, including AWS and Cloudflare for hosting, Gemini, OpenAI, Anthropic and DeepSeek for AI tools, and PostHog for analytics, with the United States as primary hosting location (18). 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): - Domain age: templated.io, registered 2023-11-13 (2 years) (7 of 15) - security.txt: not found (0 of 10) ## 7. Maintenance & community, 80 out of 100, up to 1.8 more on the total Why it scored 80: mcp-server-templated v1.7.1 tagged on 2026-09-08, 23 days before this check, and the newest changelog entry is 4 September 2026 (30). Tags v1.4.0 and v1.4.1 on 5 August and v1.7.0 and v1.7.1 on 8 September (20). Dated public changelog and support by email. We didn't check GitHub issue response (10). Listed in the official MCP registry as io.github.templated-io/mcp-server-templated, published by GitHub OIDC from CI (15). Current @modelcontextprotocol/sdk ^1.25.3 and a node test suite, but the only workflow publishes to the registry and doesn't run the tests (5). 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. ## 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 failed renders are charged, which pricing.md doesn't say - Whether video rendering is still beta after its 7 January 2026 launch - Response times on the MCP repo's GitHub issues, which we didn't check - Whether the terms include an SLA for the custom plan ## Weaknesses - One API key with full account access, and the MCP docs offer it as ?apiKey= in the URL - No OpenAPI, and no error codes or 429 handling in the API docs - No official SDKs, only code samples - No security.txt, certification or bug bounty found - AI tools send content to Gemini, OpenAI, Anthropic and DeepSeek per the privacy policy ## 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 get_template_layers before create_render so the keys in `layers` match the template - Set async true with a webhook_url for MP4, zip or batch renders, since zip without a webhook returns 400 - Video credits are width x height x fps x seconds / 50,000,000, so 10 seconds of 1080p at 30 fps costs 13 - Pass folderId or externalId on the MCP URL when one server serves several customers - Back off on your own schedule after a 429, since the docs give no retry guidance ## What the review panel asked for - Error reference with codes - Scoped keys - State failed-render billing ## 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.