# Fix list: Synthflow API + MCP From Anchor Terminal's listing at https://www.anchorterminal.com/tools/synthflow, the October 2026 research run, assessed 1 October 2026. Grade D, 51.3 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 Synthflow 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, 0 out of 100, up to 12.5 more on the total Why it scored 0: No x402, MPP or L402 (0 of 40). Sales-led only, with contracts from $30,000 a year and no published per-minute price (0). No free tier or trial for new customers (0). An agent can't get access without a sales process (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. Reliability, 45 out of 100, up to 11 more on the total Why it scored 45: Statuspage at status.synthflow.ai with incidents and maintenance back to May 2025 (20). Four incidents since 3 July 2026, 18 minutes of degraded US calling on 6 July, post-call webhook failures from 08:20 to 11:10 UTC on 7 August, 12 minutes of EU call failures on 17 August and a white-label login issue on 7 September. We count the nearly three hours of webhook failures as one major (10). Concurrency and calls-per-second limits are set per contract and no numbers are published (0). The docs say call creation can return 429 on bursts, with no Retry-After, backoff or idempotency guidance found (5 of 15). No SLA published (0). The Platform API 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. ## 3. Agent ergonomics, 45 out of 100, up to 8.9 more on the total Why it scored 45: The hosted MCP server lists 60 tools in seven groups, with no toolsets or read-only subset (5 of 25). Call and log lists filter and page (14 of 20). Errors carry codes and the new transfer failure reasons (13 of 20). Deletes need a second call with `confirmed=true`, but publish and rollback run at once and there are no annotations or idempotency keys documented (8 of 20). No official SDK packages, so agents work from raw HTTP or 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, 51 out of 100, up to 8.6 more on the total Why it scored 51: Bearer API keys created per workspace under Admin settings, with 2FA and SSO on the account. The MCP docs don't say how the server signs in (20). Deletes are confirmation-gated, but there's no read-only key and other writes run without a check (10 of 20). We found no prompt-injection guidance. PII redaction for transcripts, webhooks and logs is a separate data control (5 of 15). Call logs, and no audit log of account actions found (8 of 15). A Trust Vault at security.synthflow.ai and a public BAA template, but no security.txt, bug bounty or stated certification on the pages we read (8 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. Maintenance & community, 68 out of 100, up to 2.8 more on the total Why it scored 68: Changelog entry on 1 October 2026 (30). Ten entries between 7 September and 1 October (20). Public changelog, support we didn't test (10 of 15 for a closed service). No official SDK packages, only an MCP server and plugins (5 of 15). No packages to assess (3 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. ## 6. Transparency & trust, 68 out of 100, up to 2.8 more on the total Made of editorial 53, provenance 82. Why it scored 68: Closed platform with clear terms (15). Recordings and transcripts can be switched off or deleted after 30 days, PII redaction is available, and a BAA template is public. Default retention looks indefinite (18 of 30). Old self-serve plans are closed to new subscriptions and the changelog is dated, but we found no deprecation policy (8 of 20). Separate Global, US and EU regions are documented, and we didn't find a subprocessor list on the pages we read (12 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: synthflow.ai, registered 2023-07-21 (3 years) (7 of 15) - security.txt: not found (0 of 10) ## 7. Schema & documentation, 87 out of 100, up to 2.1 more on the total Why it scored 87: OpenAPI at docs.synthflow.ai/openapi.json (25). llms.txt with Markdown pages (10). Guides cover agents, actions and SIP connectors with when-to-use advice (14 of 20). Typed request bodies, with agent configuration as large nested objects (12 of 15). Examples throughout, and transfer failures gained nine specific reasons on 29 September 2026 (11 of 15). A dated changelog with entries most weekdays and a v2 API (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. ## 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. - The listing's toolCount of 65 didn't match the MCP page, whose seven groups add up to 60 tools. - Certifications and subprocessors in the Trust Vault, which we didn't read. - How the hosted MCP server authenticates. ## Weaknesses - Sales-led only, contracts from $30,000 a year, no free tier - No published per-minute price, concurrency or rate limits - No official SDK packages - Post-call webhooks failed for nearly three hours on 7 August 2026 - Publish and rollback through MCP run without confirmation ## 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 MCP and API base URL that matches the workspace region (Global, US or EU) - Send destructive MCP tools again with `confirmed=true` after a person approves - Expect 429 on call bursts, since `POST /v2/calls` is limited by calls per second as well as concurrency - Read the transfer failure reason on a failed transfer before retrying it ## What the review panel asked for - publish default limits - document 429 handling - confirmation on publish - a public certification list ## 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.