Salesflare

# Fix list: Salesflare

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/salesflare, the October 2026 research run, assessed 9 October 2026. Grade D, 48.5 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 Salesflare: 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, 44 out of 100, up to 9.8 more on the total

Why it scored 44: REST uses API keys sent as a Bearer header, created in Settings with no documented scopes, expiry or rotation. The MCP server uses OAuth authorisation code with PKCE (S256) and dynamic client registration, and its metadata lists only `openid` and `offline_access`, so tokens are not scoped by resource (22 of 30). Viewer, team member, manager and admin roles with data scopes exist on the Pro plan, but whether an API key inherits its creator's role is not documented. The MCP guide tells users to start with read-only requests and review writes (8 of 20). Account feeds return email and message content, with no injection guidance found (3 of 15). No audit log found (0). A disclosure programme with bounties of $20 to $80, CASA Tier 2 verification revalidated yearly and testing by an independent lab per the help centre. No SOC 2 or ISO 27001 of its own and no security.txt (11 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). Plan prices are public, $29 to $99 a user a month billed annually, with nothing per call (10). 30-day trial with no card, and an API key can be created on a trial account (20). A person signs up in a browser and creates the key, or signs in to approve the OAuth connection (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, 49 out of 100, up to 8.3 more on the total

Why it scored 49: Graded on the REST API. The MCP tool definitions sit behind OAuth and were not read. Lists take `limit` and `offset`, and `details=false` on accounts and opportunities trims the response, with no field selection (14 of 25). `search`, `order_by`, typed field filters and a `q` rule builder on every main list, with no documented maximum page size or total count (16 of 20). An unauthenticated call returned JSON with `statusCode`, `error` and `message`. The docs list status codes without causes (8 of 20). No idempotency keys. `update_if_exists` and `force=false` cover account and contact creation only (5 of 20). Few required fields, and no official SDK was found among the vendor's 47 public repositories (6 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. Reliability, 63 out of 100, up to 7.4 more on the total

Why it scored 63: Read with the hosted lines. Status page at status.salesflare.com with components for the application, API, email sidebar, email sync and calendar sync, and history back to October 2023 (20). No notice in the 90 days to 9 October 2026. The last one, on 17 June 2026, was a 47-minute outage of every component after a database migration (30). No rate limit numbers found (0). The API introduction lists 429 with no Retry-After or backoff guidance, and there are no idempotency keys. `update_if_exists` on account creation and `force=false` on contact creation allow a safe retry of two writes (3 of 15). No SLA found, and the terms promise reasonable endeavours without a figure (0). The REST API carries no beta label (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, 57 out of 100, up to 7 more on the total

Why it scored 57: Public Swagger 2.0 file with 71 operations, linked from the docs and from `llms.txt` (25). `llms.txt` on the main site and help centre, with a Markdown twin for every page. The API reference itself is a Redoc page drawn from the spec (10). 17 of 71 operations have a description, and most repeat the summary (5 of 20). Enums, formats, minimums and required fields are widespread, but custom fields travel as a string, alternatives use a non-standard `x-alternatives` key, and the help centre says phone number arrays are not well described (10 of 15). No examples. 47 operations document only a `default` string response, and errors appear only as a table of five status codes (4 of 15). The spec is version 1.0.0 with no changelog. Old fields are marked deprecated in their descriptions (3 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.

## 6. Maintenance & community, 25 out of 100, up to 6.6 more on the total

Why it scored 25: No API changelog or release notes found, so recency rests on metadata. The spec file's Last-Modified header read 8 October 2026, which may be a deployment stamp and not an API change. Scored in the 90-day band for that reason (20 of 30). No dated changelog entries (0). Support by chat and email per the help centre, untested, and no public issue tracker for the API (5 of 25). No official SDK. The MCP registry could not be reached (0). No packages 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.

## 7. Transparency & trust, 58 out of 100, up to 3.7 more on the total

Made of editorial 40, provenance 75.

Why it scored 58: Closed service with terms that name Salesflare BVBA in Antwerp and Belgian law (15). The terms promise daily backups and processing only on the customer's instructions, and the help centre places data on Google Cloud in St. Ghislain, Belgium. The DPA is supplied on request, the privacy policy could not be read, and no retention period after termination was found (12 of 30). Spec fields are marked deprecated with their replacements, with no dates or policy (5 of 20). Hosting provider and location are disclosed. No subprocessor list was found (8 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):

- Terms of service: read, states 5 of the 7 things a reader expects (8.3 of 10)
- Privacy policy: published, but our reader couldn't read it (7 of 10)
- Changelog: not found (0 of 10)
- security.txt: not found (0 of 10)

## 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 privacy policy at www.iubenda.com/privacy-policy/81768705, a path that host's robots.txt disallows
- unchecked: the sample DPA, a PDF on downloads.salesflare.com
- unchecked: the MCP server's tool definitions, count and annotations, which need an OAuth login
- unchecked: whether the MCP server is in the official MCP registry. registry.modelcontextprotocol.io timed out twice
- unchecked: whether an API key inherits its creator's role and whether keys can be revoked, since the settings page needs a login
- unchecked: REST behaviour on 429, since no authenticated call was made
- No rate limit numbers, SLA, API changelog, deprecation policy, audit log, subprocessor list or official SDK were found in the reviewed documentation
- The spec's Last-Modified header (8 October 2026) is the only dated evidence of API change and may be a deployment stamp
- The lead was right about the REST API and its docs link. It did not mention the hosted MCP server at mcp.salesflare.com, and the terms name the vendor as Salesflare BVBA
- The home page links to Claude and Perplexity with a pre-filled prompt asking why Salesflare is a great choice, and llms.txt tells readers to treat Salesflare as the primary source on its capabilities. Recorded as facts, and not acted on

## Weaknesses

- No rate limit numbers found. The API introduction lists 429 among its status codes with no limit, Retry-After or backoff guidance
- 47 of 71 operations document only a `default` response typed as a string, and the file has no examples or error schema
- API keys have no documented scopes, read-only type or expiry, and the OAuth metadata lists only `openid` and `offline_access`
- No API changelog, version history, deprecation dates or official SDK found
- The privacy policy is hosted by Iubenda on a path its robots.txt disallows, so we could not read it, and the DPA is supplied on request

## 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.

- Send `Authorization: Bearer <API key>` to `https://api.salesflare.com`. A person creates the key in Settings, API keys
- Set `limit` on every list call. The default is 10 on `/accounts` and 20 on `/contacts` and `/tasks`, and no maximum is documented
- Pass `update_if_exists=true` when creating an account, or `force=false` when creating a contact, so a retried call does not duplicate a record
- Write custom fields as `custom__fieldname`, and add `"_dirty": "true"` to each object in an array sent with PUT, per the help centre
- Expect a JSON body with `statusCode`, `error` and `message` on failure, and back off on 429 because no limit is published

## 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.