# Fix list: Agenda Hero From Anchor Terminal's listing at https://www.anchorterminal.com/tools/agenda-hero, the October 2026 research run, assessed 21 October 2026. Grade F, 34.5 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 Agenda Hero: 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. Schema & documentation, 18 out of 100, up to 13.3 more on the total Why it scored 18: The MCP tool definitions need a signed-in token and weren't read, so the typed-schema line is unchecked (0 of 25). No llms.txt or Markdown docs for agents (0). The help page says what each tool does and where it stops, such as read-only source events, whole-series edits and place IDs only from a lookup, which is documentation for people rather than tool descriptions (8 of 20). Typed inputs unchecked (0 of 15). Sample prompts but no documented error responses (5 of 15). Dated product posts and App Store notes, with no versioning for the connector (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. ## 2. Reliability, 35 out of 100, up to 13 more on the total Why it scored 35: Read with the hosted lines, for the MCP server. A status page at status.agendahero.com (20). Its history is drawn by script and couldn't be read (5). No rate limits published for the connector or the app (0). No overload or retry guidance (0). No SLA (0). The connector is live in ChatGPT's plugin directory and not labelled beta (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. ## 3. Agent ergonomics, 28 out of 100, up to 11.7 more on the total Why it scored 28: Context cost. The help page lists about seven actions, which suggests a compact toolset, but the definitions weren't read (10 of 25). Events can be read for a date range (8 of 20). Errors. The unauthenticated 401 carries a WWW-Authenticate header with resource metadata; tool errors aren't documented (5 of 20). Annotations unchecked, and removals are immediate and permanent with no review step (0 of 20). Calendar time zone is the default, and there are no SDKs, only the MCP server (5 of 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. ## 4. Security & auth, 38 out of 100, up to 10.9 more on the total Why it scored 38: Credential model. OAuth with three scopes (calendars:read, events:read, events:write), PKCE S256, dynamic registration and a revocation endpoint, from Agenda Hero's own metadata (30). Least privilege. The assistant can change only calendars the person can edit and only reads events from sources, but the consent screen grants all three scopes together and deletions run with no confirmation (8 of 20). Injection. Tools return event text from schools, teams and other people's calendars and no guidance on untrusted content was found (0 of 15). No audit log or per-call view for the operator found (0 of 15). No security.txt, disclosure policy, bounty or certification found (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. ## 5. Payments & pricing, 30 out of 100, up to 8.8 more on the total Why it scored 30: No x402, MPP or L402 (0). Plan prices are public, Plus US$5, Family US$10 and Organizations US$20 a month, with no per-unit price (10). Free forever with no card, and the connector works on free accounts (20). A person signs up and approves the connection 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. ## 6. Transparency & trust, 52 out of 100, up to 4.2 more on the total Made of editorial 18, provenance 86. Why it scored 52: The terms are an iubenda embed whose path iubenda's robots.txt disallows, so the licence line is unchecked and scored absent (0 of 30, unchecked). The privacy page on agendahero.com says prompts go to OpenAI or Anthropic, no data is shared for third-party model training, and Google data is removed when the person disconnects; no retention periods were readable (12 of 30). No deprecation policy or dated notices found (0 of 20). OpenAI and Anthropic are named; hosting and locations aren't (6 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): - Domain age: agendahero.com, registered 2020-01-17 (6 years) (11 of 15) - security.txt: not found (0 of 10) ## 7. Maintenance & community, 58 out of 100, up to 3.7 more on the total Why it scored 58: Read for a closed service. iOS 2.2.0 on 20 October 2026 and the MCP connector on 16 October (30). iOS 2.0.0 on 24 September, 2.1.0 on 29 September and 2.2.0 on 20 October, plus eight dated posts in October (20). A public product blog, a contact page and App Store notes that say what changed (8 of 15). Not in the official MCP registry, searched for agendahero and agenda-hero on 21 October 2026 (0). No package to judge (0). 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. - unchecked: the terms of service and full privacy policy, on iubenda paths its robots.txt disallows. - unchecked: the MCP tool definitions, annotations and error shapes, which need a signed-in token. - unchecked: status.agendahero.com's incident history, which is drawn by script. - Whether a read-only grant is possible, since the consent screen lists all three scopes. ## Weaknesses - Deletions and edits save immediately with no review step, and removed events can't be restored. - One consent grants read and write together, with no read-only option documented. - Tools return event text written by schools and other calendar owners, with no injection guidance. - Terms of service couldn't be read, and no security contact was found. ## 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. - Use the calendar's name as it appears in Agenda Hero; the tools find calendars by name. - Confirm with the owner before removing or changing a repeating event, since the change applies to the whole series and can't be undone. - Don't try to edit events that come from a source calendar. They're read-only here and must be changed where they live. - Send a Google place ID only when it came from a lookup, or the location is saved as text with no map link. ## What the review panel asked for - read-only scope option - a versioned connector changelog - public tool definitions - publish the tool schemas - add an llms.txt - a read-only grant - an undo for deletions ## 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.