LeadMagic API + MCP by LeadMagic

# Fix list: LeadMagic API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/leadmagic, the October 2026 research run, assessed 1 October 2026. Grade C, 60.5 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 LeadMagic 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, 20 out of 100, up to 10 more on the total

Why it scored 20: No x402, MPP or L402 (0). Plan prices and per-endpoint credit costs are public (20). No free tier or trial credits, only a 14-day money-back guarantee on a paid first month (0). A person signs up and pays 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.

## 2. Reliability, 55 out of 100, up to 9 more on the total

Why it scored 55: Own status page at leadmagic.io/status listing the REST API, web app, Email Finder, Mobile Finder, Email Validation and integrations, with a live API health check but no incident history (10 of 20). No history to read (5). Per-second and per-day limits published, 5 or 10 requests a second for credit-free search with a fair-use ceiling of 13,333 searches a day (15). 429 carries Retry-After with advice to back off, and 400s aren't charged (15). The Service Level and Availability Policy states there's no guaranteed uptime and service credits are discretionary (0). 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. Security & auth, 60 out of 100, up to 7 more on the total

Why it scored 60: REST keys prefixed `lm_` in the `X-API-Key` header. The hosted MCP is OAuth only and refuses static keys. No key scopes found (22 of 30). The tools are lookups and bulk job submissions with no deletes, but no read-only mode or confirmation step (12 of 20). Results include ad copy, job posts and company descriptions from the open web, and we found no injection guidance (4 of 15). `X-Credits-Cost` and `X-Credits-Remaining` on every response, `request_id` on errors, and an account analytics tool (12 of 15). security.txt valid per the 30 September check. The DPA promises breach notice within 72 hours. No SOC 2 or bug bounty found (10 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.

## 4. Agent ergonomics, 61 out of 100, up to 6.3 more on the total

Why it scored 61: The hosted MCP has 48 tools, 3 prompts and a docs resource, with no toolsets or dynamic loading found (5). A free `preview_cost` tool and browse pages of up to 25 rows help a little (8 of 25). Search filters and pages (16 of 20). Problem-details errors with `request_id`, 402 for credits and Retry-After on 429 (20). Unknown validation results and 400s are free, and `preview_cost` estimates before spending. No idempotency keys or tool annotations found (10 of 20). No official SDKs found. A terminal client, lm-tui, shares the credits (7 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.

## 5. Maintenance & community, 65 out of 100, up to 3.1 more on the total

Why it scored 65: api 3.3.1 on 2026-09-17 (30). Four dated entries in the last 90 days, on 19 July, 25 August (two) and 17 September (20). Public changelog and support, issue handling not visible (10 of 15). Not in the official MCP registry and no official SDKs found (0). No packages to judge (5 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, 66 out of 100, up to 3 more on the total

Made of editorial 47, provenance 85.

Why it scored 66: Closed service with terms naming Lead Magic Corporation, Massachusetts (15). The privacy policy covers people returned by the API and links a request form, a do-not-sell page and privacy@leadmagic.io. We found no stated legal basis, data sources or retention periods in it. The DPA uses SCCs and the UK IDTA (14 of 30). Changelog entries are dated, but no deprecation policy or notices found (6 of 20). The DPA points to a subprocessor list with 15 days' notice of changes and says data is processed in the US and elsewhere (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: leadmagic.io, no registry record we could read (0 of 15)

## 7. Schema & documentation, 93 out of 100, up to 1.1 more on the total

Why it scored 93: OpenAPI file at leadmagic.io/openapi.json, per the 30 September check (25). llms.txt (10). MCP tools state their purpose and credit cost, and the server tells the model to report only data the tools returned (16 of 20). Typed request bodies (12 of 15). RFC 9457 problem details with a `request_id` on every error, and documented 400, 401, 402 and 429 cases (15). A dated changelog versioned per component, api 3.3.1 on 2026-09-17 (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 said 20,000 credit-free searches a day. The 17 September 2026 changelog and the docs now say 13,333, and we've patched notable and details
- Whether API keys can be scoped or rotated
- unchecked: the subprocessor list itself, which the DPA references
- Whether the MCP's 48 tools carry readOnlyHint annotations

## Weaknesses

- No free tier or trial credits, plans from $99 a month
- The service-level policy disclaims any uptime guarantee
- Status page has no incident history
- 48 MCP tools with no toolsets or read-only subset
- Privacy policy states no legal basis, data sources or retention periods that we could find

## 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.

- Call `preview_cost` before bulk work. It's free
- Read `X-Credits-Remaining` after each call instead of polling the balance
- Treat 402 as out of credits and wait out Retry-After on 429
- Keep credit-free search under 13,333 calls a day per account
- Retry `unknown` validations later. They cost nothing

## What the review panel asked for

- add a small free trial
- read-only toolset
- scoped API keys

## 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.