ContactsPlus

# Fix list: ContactsPlus

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/contactsplus, the October 2026 research run, assessed 14 October 2026. Grade E, 42.4 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 ContactsPlus: 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. Reliability, 28 out of 100, up to 14.4 more on the total

Why it scored 28: Graded with the hosted lines, on the REST API and the MCP server. The status page at /status/ is a static page listing seven services, last updated 26 June 2026, with no component history (10 of 20). It says no incidents in the past 90 days, but a page last updated in June can't show that (5). No rate limits found in the API reference (0). No 429 or retry guidance. Update and delete take an etag, which guards against overwriting a newer record (3 of 15). No SLA found (0). Neither the API nor the MCP server carries a 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.

## 2. Schema & documentation, 38 out of 100, up to 10.1 more on the total

Why it scored 38: No OpenAPI or other machine-readable contract, and the MCP tool schemas couldn't be read without signing in (0). A site llms.txt lists the developer pages, but the API reference isn't served as Markdown (5 of 10). The reference says what each call does in a line or two, and the MCP page says which tools read, propose or apply (12 of 20). Fields are typed in the docs, with no enums for labels or webhook triggers (8 of 15). curl, Clojure and JavaScript examples for every call, but no documented error responses (8 of 15). Versioned paths under /api/v1 and /v3/oauth, with no changelog (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.

## 3. Agent ergonomics, 42 out of 100, up to 9.4 more on the total

Why it scored 42: No field selection. contacts.scroll takes a size, and MCP reads are paged and capped (12 of 25). Cursor paging on scroll and search, tag filters and team scoping (15 of 20). Error responses aren't documented (0). etags on update and delete, Create Tag returns an existing tag rather than a duplicate, and MCP writes wait in Suggestions for approval. MCP annotations couldn't be checked (12 of 20). The only clients, for Node and Clojure, were last published in 2020 and are archived (3 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. 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, but no API price is named and the MCP needs Premium (10). A free plan with no credit card, and the developer page says the API is free to start (20). A person signs up and registers an app 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.

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

Why it scored 25: The AI assistants (MCP) page was last modified on 28 September 2026 per the sitemap, and the terms and privacy policy on 26 June 2026. No dated release was found, so this is a soft signal (20). No changelog, so no dated releases to count (0). A help centre and support address but no public changelog or developer forum (5 of 15). The API clients are archived and last released in 2020 (0). No current package or CI to check (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.

## 6. Security & auth, 71 out of 100, up to 5.1 more on the total

Why it scored 71: OAuth 2.0 with 10 scopes that split reads from writes for contacts, tags and team data. The MCP server uses OAuth with PKCE and dynamic client registration (30). The MCP server has Read only and Full access modes, can't delete or export, and holds field changes, notes and new contacts for the owner's approval value by value. Only tagging applies at once (20). It never fetches links or reads images, but no prompt-injection guidance was found for contact text (8 of 15). The Suggestions queue shows each proposed change, with no audit log found for API calls (5 of 15). A responsible disclosure policy with security@contactsplus.com and OpenBugBounty and discretionary bounties, no security.txt and no SOC 2 or ISO 27001 found (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.

## 7. Transparency & trust, 62 out of 100, up to 3.3 more on the total

Made of editorial 48, provenance 75.

Why it scored 62: Closed service under terms dated 26 June 2026, which grant developers an API licence (15). The privacy policy and security page agree on retention of up to five years after last use, deletion on request, AES-256 at rest and AWS hosting, and disclose that contacts are combined with other users' data and public sources, with an opt-out (20 of 30). Terms promise 30 days' notice of material changes, with no API deprecation policy found (5 of 20). Stripe, Google Analytics and AWS are named, but no sub-processor 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 4 of the 7 things a reader expects, and has 1 clause that costs points (5.4 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 MCP tool definitions and annotations, which need a signed-in session
- Why the MCP server's metadata advertises only read scopes when a Full access mode is described
- unchecked: whether the REST API is available on the free plan without limits, since the pricing page doesn't mention it
- unchecked: when the MCP server launched, since no dated announcement or changelog was found

## Weaknesses

- No rate limits, error responses or changelog in the API reference
- No OpenAPI spec, and MCP tool schemas aren't public
- Node and Clojure clients last released in 2020 and archived
- Status page is a static page last updated 26 June 2026
- MCP access needs the Premium plan

## 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.

- Pass the contact's current etag on update and delete, or the call will be refused
- Use contacts.scroll with includeDeletedContacts to keep a copy in step, or subscribe to webhooks
- Tell the user that MCP edits land in Suggestions and need their approval
- Ask only for contacts.read and tags.read when the task is lookup
- Search with field criteria such as company:Acme AND title:CTO to keep results small

## 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.