# Fix list: Supermemory API + MCP From Anchor Terminal's listing at https://www.anchorterminal.com/tools/supermemory, the October 2026 research run, assessed 1 October 2026. Grade B, 63.6 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 Supermemory 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. Payments & pricing, 30 out of 100, up to 8.8 more on the total Why it scored 30: No x402, MPP or L402. An empty balance returns 402 with no payment payload (0). Per-unit prices without a login, $5 per million SM tokens for plain-text memory, $10 for rich content, $5 per million searches, $100 per million operations (20). Free has $5 of credit renewed monthly, and the pricing page doesn't say whether a card is needed (10 of 20). A person signs up in the console, and the MCP signs in through 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. ## 2. Security & auth, 54 out of 100, up to 8.1 more on the total Why it scored 54: Org keys have full access, but scoped keys can be limited to one or more containerTags, set to expire in 1 to 365 days and revoked (401 after). The MCP signs in with OAuth and asks which spaces to allow (28 of 30). Scoped keys can't read billing, change settings or mint keys, MCP spaces carry read or write permission, and the mass forget has a dry run, but there's no read-only key (14 of 20). Supermemory ingests URLs, PDFs and web pages and returns them to the model, and we found no prompt-injection guidance (0). An analytics page exists in the docs, and we couldn't confirm per-call logs (0). SOC 2 Type II, GDPR and a HIPAA BAA per the security page. No security.txt, disclosure policy or bug bounty found (12 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. ## 3. Reliability, 65 out of 100, up to 7 more on the total Why it scored 65: incident.io status page at status.supermemory.ai tracking the API and the Console, with a calendar history (20). Both components show 100 per cent from July to October 2026 and no incidents (30). No rate limits found in the docs, the pricing page or the changelog (0). No 429 or retry guidance found. A 402 on an empty balance is documented, which isn't overload handling (0). Enterprise lists an "Uptime SLA" with no figure (5 of 10). 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. ## 4. Transparency & trust, 49 out of 100, up to 4.5 more on the total Made of editorial 43, provenance 55. Why it scored 49: The MIT repo runs the engine locally as one binary, and the hosted service is closed (20 of 30). The security page says customer content never trains models on any plan, and erasure works by deleting a container tag. Forget on a single memory is a soft delete, the terms (2 June 2025) and privacy policy (4 June 2025) name no company, and we found no retention periods (15 of 30). v3 and v4 run side by side and the changelog says versioned paths are unchanged, but there's no deprecation policy or dated notice (8 of 20). No subprocessor list or data locations found (0). 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): - Legal entity named: not found (0 of 20) - Domain age: supermemory.ai, no registry record we could read (0 of 15) - security.txt: not found (0 of 10) ## 5. Agent ergonomics, 73 out of 100, up to 4.4 more on the total Why it scored 73: 8 MCP tools, among them who_am_i to check permissions (25). Search and list calls filter by containerTag, and we didn't confirm page-size caps (15 of 20). 402 for an empty balance and 401 for a revoked key are documented, without a wider error list (10 of 20). We found no idempotency keys or MCP annotations. Forget is a soft delete and the mass forget has a dryRun preview, which makes mistakes recoverable (8 of 20). TypeScript and Python SDKs, and an add needs only content (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. Schema & documentation, 85 out of 100, up to 2.4 more on the total Why it scored 85: OpenAPI at api.supermemory.ai/v4/openapi, and since 23 August 2026 also at /openapi.json (25). llms.txt with a one-line purpose per endpoint (10). Endpoint descriptions say what each does and some say when to use it, such as running the prompt-based mass forget with dryRun first (14 of 20). Typed inputs with enums for dreaming and searchMode and stated limits of 100 characters for containerTag and customId (12 of 15). Quickstart examples and a documented 402, but we found no error catalogue (9 of 15). v3 and v4 paths and a dated API changelog (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. ## 7. Maintenance & community, 85 out of 100, up to 1.3 more on the total Why it scored 85: Last API changelog entry on 2026-09-21 (30). 14 dated entries since 3 July (20). 22 open issues and 93 open pull requests on the MIT repo, with reply times we didn't check (12 of 25). Current TypeScript and Python SDKs (15). The hosted MCP isn't in the official registry. GitHub Actions workflows in the repo, with status unchecked (8 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. ## 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 Free plan needs a card isn't stated on the pricing page. - We couldn't confirm what the analytics page records per call. - We didn't re-check the npm and PyPI release dates, so lastRelease stays at the changelog date of 2026-09-21. - The terms check (no legal entity) comes from the listing check on 2026-09-30. ## Weaknesses - No legal entity named in the terms or privacy policy - No published rate limits or 429 guidance - Ingests web pages and PDFs with no prompt-injection guidance found - v3 and v4 endpoints live side by side, so examples disagree - No security.txt and no official MCP registry entry ## 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 one stable `containerTag` per user and a `customId` per session - Poll the document until `status` is `done` before searching for what you just added - Treat a 402 on search or profile as out of credit, not as a bug - Run the prompt-based mass forget with `dryRun` first - Call who_am_i on the MCP to see which spaces you can write to before adding ## What the review panel asked for - Retire old examples - Publish an error catalogue - guidance on ingested pages - a named contracting entity ## 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.