Prospeo API + MCP by Prospeo

# Fix list: Prospeo API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/prospeo, the October 2026 research run, assessed 1 October 2026. Grade D, 51.1 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 Prospeo 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. Reliability, 35 out of 100, up to 13 more on the total

Why it scored 35: No status page found, and status.prospeo.io doesn't resolve in DNS as of 2 October (0). No incident history to read (5). Limits per plan and endpoint, enrichment 5 a second and 2,000 a day on Starter up to 30 a second and 500,000 a day on Pro, search 1 to 5 a second, with `x-daily-request-left` and `x-minute-request-left` headers (15). 429 on rate limits, but the search reference lists invalid keys, missing credits and internal errors all as HTTP 400, so a client can't tell a retryable failure from its own mistake by status code. No Retry-After or back-off guidance found (5 of 15). No SLA found (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.

## 2. Security & auth, 54 out of 100, up to 8.1 more on the total

Why it scored 54: Keys in the `X-KEY` header, several keys per account. The hosted MCP takes OAuth or the same header (22 of 30). Every tool reads, and the MCP marks them so (16 of 20). Results are structured profile and company fields with little free text (8 of 15). Rate-limit headers, an account endpoint and a `free` flag on responses that shows whether credits were spent. No per-call log found (8 of 15). No security.txt, disclosure policy, bug bounty or certification found (0 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. Payments & pricing, 40 out of 100, up to 7.5 more on the total

Why it scored 40: No x402, MPP or L402 (0). Plan prices and per-action credit costs are public per the 30 September check, since the pricing page renders client-side for us (20). Free plan with 100 credits a month, and the docs say API access is free for all users (20). A person signs up 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.

## 4. Schema & documentation, 61 out of 100, up to 6.3 more on the total

Why it scored 61: No OpenAPI file for the REST API. The MCP tools carry full JSON Schema inputs generated from zod (15 of 25). No llms.txt found (0). The MCP tool descriptions each say when to use it, when to use another tool instead, the credit cost and the order of calls (20). Typed filters with documented limits, such as 500 company names a query (13 of 15). Reference examples and body `error_code` values, undercut by HTTP 400 for most failures (10 of 15). No changelog or versioning. The docs carry 'last updated 11 June 2026' (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.

## 5. Maintenance & community, 34 out of 100, up to 5.8 more on the total

Why it scored 34: Newest MCP release 1.1.0 on 2026-06-01, still the last commit in the repository on 2 October, and the API docs were last updated on 2026-06-11, between 90 and 180 days ago (10). No releases or dated entries in the last 90 days (0). No changelog, and the MCP repo's commits are all from staff. We couldn't see issue handling from git (5 of 25). Listed in the official MCP registry as io.prospeo/prospeo-mcp-server, a domain-verified namespace (15). The MCP repo has vitest tests but no CI workflow and no tags (4 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, 45 out of 100, up to 4.8 more on the total

Made of editorial 34, provenance 55.

Why it scored 45: The MCP server is MIT. The API is closed, run by Defastra Tech Inc. doing business as Prospeo per the privacy policy (18 of 30). The privacy policy and terms render client-side and were unreadable to us on 1 and 2 October, and the Wayback Machine is blocked to our reader. Per the 30 September check the privacy policy takes a perpetual, irrevocable licence to ingest and retain contact data from customer uploads, which feeds customer data into the shared database (8 of 30). Legacy endpoints were deprecated and removed in March 2026 per the 30 September check. The old Email Finder docs URL now opens the REST API introduction, with no notice text left to date the warning, and no deprecation policy found (8 of 20). The terms page's metadata mentions sub-processors, but we couldn't read a list or data locations (0 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: prospeo.io, no registry record we could read (0 of 15)
- Status page: not found (0 of 10)
- Changelog: not found (0 of 10)
- security.txt: not found (0 of 10)

## 7. Agent ergonomics, 79 out of 100, up to 3.4 more on the total

Why it scored 79: 8 MCP tools, but their filter schemas come from 44 kB of zod source, so tools/list is heavier than the count suggests. Bulk enrichment returns a compact record per person (20 of 25). 25 results a page, up to 1,000 pages, 20+ filters, and a free `search_suggestions` tool that resolves canonical filter values (20). Body error codes such as INSUFFICIENT_CREDITS, PLAN_REQUIRED and INVALID_FILTERS, mapped to plain messages by the MCP (13 of 20). Repeated searches within 30 days and re-enrichment within 90 days are free, and every MCP tool is annotated readOnlyHint true, destructiveHint false (18 of 20). At least one include filter is required. The MCP package is the only official client (8 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.

## 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, terms and pricing, which render client-side and came back empty again on 2 October, with the Wayback Machine blocked to our reader. Payments (plan prices) and transparency (the perpetual licence to uploaded data) rely on the 30 September check.
- unchecked: subprocessors and data locations. The terms page's metadata mentions sub-processors, but the list isn't readable to us.
- No status page found. status.prospeo.io doesn't resolve, and neither the API docs nor the MCP README link one.
- unchecked: the notice period before the March 2026 removal of the legacy endpoints. The old Email Finder URL now opens the REST API introduction, with no notice text.

## Weaknesses

- No status page, SLA or changelog
- Most errors, including internal ones, return HTTP 400
- No OpenAPI file or llms.txt for the REST API
- No MCP release or docs update since June 2026
- Privacy policy takes a perpetual licence to uploaded contact data, per the 30 September check

## 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 `search_suggestions` before using location, technology or industry filters, or the search returns nothing
- Pass `person_id` values from search into `bulk_enrich_person`, 25 at a time
- Branch on the body `error_code`, not the HTTP status, which is 400 for most failures
- Set `enrich_mobile` only when needed. A mobile costs 10 credits against 1 for an email
- Use Enrich Person. The old Email Finder endpoint was removed in March 2026

## What the review panel asked for

- Serve pricing as static HTML
- Publish a schema token count
- publish a security.txt
- define what counts as upload

## 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.