Apollo API + MCP by Apollo.io

# Fix list: Apollo API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/apollo, the October 2026 research run, assessed 1 October 2026. Grade B, 63.6 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 Apollo 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, 30 out of 100, up to 8.8 more on the total

Why it scored 30: No x402, MPP or L402 (0). Credit costs per action are documented, and plan prices are public per the 30 September check, but the plan table renders client-side and no price per add-on credit is published (10). Free plan with API rate limits listed in the docs. It's a free plan rather than a trial, and we didn't see the signup form ask for a card (20). A person signs up in a browser with a work email (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, 65 out of 100, up to 7 more on the total

Why it scored 65: Status page at status.apollo.io with eight components and incident history (20). The feed lists 15 entries since 7 July 2026. Most are short Background Jobs Latency downtimes of 30 to 49 minutes, but two ran over an hour (1 h 16 min on 3 August, 2 h 49 min on 6 September), and maintenance windows reached 9 h 35 min on 1 August. No component covers the REST API or the MCP server, so API outages wouldn't show (10). Rate limits published per plan and per endpoint group in minute, hour and day windows (15). 429s carry `retry-after`, and `error_details.suggestions` includes `retry_after_seconds`. No idempotency or safe-retry guidance for the write endpoints (10 of 15). No SLA found (0). REST and MCP are generally available, 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.

## 3. Security & auth, 60 out of 100, up to 7 more on the total

Why it scored 60: Keys sent in the `x-api-key` header. Scoped keys are the default and are limited to chosen endpoints (403 elsewhere), and keys can be regenerated or deleted. OAuth for the MCP in chat clients. Headless MCP use needs a master key that reaches every endpoint (25 of 30). Scoped keys give least privilege on REST. The MCP has 13 write actions, including sending one-off emails, adding contacts to sequences and buying domains and mailboxes, with no read-only mode, and approval is left to the client (10 of 20). Results include third-party-sourced profile text, emails and call transcripts, and we found no prompt-injection guidance (3 of 15). Usage stats endpoint, rate-limit usage headers, and audit logging listed in the trust centre (8 of 15). ISO 27001 and SOC 2 Type 2 per the SafeBase trust centre, disclosure by email to security@apollo.io, no bug bounty found, no security.txt (14 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, 65 out of 100, up to 5.7 more on the total

Why it scored 65: People search pages hold up to 100 records and stop at 500 pages. We found no field selection, and the hosted MCP lists about 48 actions, a heavy tools/list for an agent that only prospects (12 of 25). Pagination and dozens of search filters (20). `error_details` gives a stable code, a message, ordered suggestions and the request values that caused the refusal, which an agent can act on (20). No idempotency keys and no readOnlyHint or destructiveHint confirmed for the MCP actions (5 of 20). Few required parameters, but no official SDKs, only the REST API, an Apollo CLI and the MCP (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.

## 5. Maintenance & community, 58 out of 100, up to 3.7 more on the total

Why it scored 58: Newest changelog entry, structured API errors, on 2026-09-18 (30). Only one dated changelog entry in the last 90 days. The MCP plugin repo has commits on 20 July and 16 September, which aren't releases (0). Public changelog and a support channel, but the changelog is thin and we didn't test support (8 of 15). Listed in the official MCP registry as io.github.apolloio/apollo-mcp, a GitHub-verified namespace, version 0.1.1 published 2026-07-20 (15). No SDK packages to judge. The plugin repo has a registry publish workflow (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, 75 out of 100, up to 2.2 more on the total

Made of editorial 64, provenance 86.

Why it scored 75: Closed service with published terms naming ZenLeads Inc. d/b/a Apollo.io. The MCP plugin repo is MIT (15). The privacy policy (updated 10 August 2026) names its data sources (public websites, third-party providers, customer submissions), relies on legitimate interests, routes deletion through a privacy centre and privacy@apollo.io, and links a DPA. Retention is 'consistent with the purposes', with no periods (22 of 30). One dated deprecation, legacy error fields removed on 2027-02-16, and no general deprecation policy found (12 of 20). The trust centre names subprocessors (Databricks, Snowflake, OpenAI, AWS, Google Cloud), and transfers rely on SCCs and the EU-US Data Privacy Framework (15 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: apollo.io, registered 2018-01-09 (8 years) (11 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 3.1 file at docs.apollo.io/openapi/apollo-rest-api.json, per the 30 September check (25). llms.txt with 51 links and Markdown twins of every page (10). Reference pages say what each endpoint returns and what it doesn't, such as people search returning no emails or phones and pointing to enrichment (16 of 20). Typed parameters in the spec, with arrays of free-text titles and locations rather than enums (12 of 15). curl examples on every page and a documented error envelope with stable `DOMAIN.CATEGORY.REASON` codes and remediation suggestions (14 of 15). Public changelog, but it holds a single entry dated 2026-09-18, and the API has no version scheme beyond v1 (10 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.

## 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 MCP docs page listed about 48 actions on 1 October, against 51 in the listing. The server's own tools/list wasn't checked
- The pricing page now names Free, Basic, Professional and Custom tiers, while the API rate-limit table still has an Organization plan. We couldn't read the client-rendered plan prices to confirm $49, $79 and $119
- Which plans get API access in practice, given the pricing FAQ and the API docs disagree
- unchecked: whether the MCP actions carry readOnlyHint or destructiveHint annotations

## Weaknesses

- Headless MCP use needs a master key that reaches every endpoint
- MCP write actions include sending email, sequence enrolment and buying domains, with no read-only mode
- Status page has no API or MCP component, and logged background-job downtimes of 1 h 16 min and 2 h 49 min in the last 90 days
- Pricing FAQ says API access is on Custom plans, while the API docs list limits for Free through the Organization plan
- One changelog entry and no SLA found

## 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.

- Search people first at 0 credits, then enrich only the people you'll contact
- Branch on `error_details.code` and wait `retry_after_seconds` from the suggestions after a 429
- Limits are per team, so read the `x-minute-usage` and remaining headers before a bulk run
- Use a scoped key with only the endpoints the job needs. A master key reaches everything
- Get a person's approval before adding contacts to a sequence, since enrolment can start sending

## What the review panel asked for

- publish a price per add-on credit
- cap waterfall credits per lookup
- read-only MCP mode
- scoped keys for MCP

## 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.