Explorium AgentSource

# Fix list: Explorium AgentSource

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/explorium-agentsource, the October 2026 research run, assessed 9 October 2026. Grade D, 48.1 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 Explorium AgentSource: 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, 42 out of 100, up to 11.6 more on the total

Why it scored 42: Hosted lines. No status page found. The docs tell users to subscribe to status updates and link no page, and status.explorium.ai did not answer (0). No readable incident history (5). Rate limit published, 200 queries a minute per key over a 60-second sliding window, with each batch entity counted as a query (15). 429s carry `Retry-After` and `X-RateLimit-*` headers and the docs ask for exponential backoff. No idempotency keys were found for the webhook and enrolment writes (12 of 15). No SLA is published. The migration guide implies one exists by saying v1 loses its SLA at end of support (0). v2 reached general availability on 2 September 2026, though the conventions page still says request and response schemas are being finalised (10). Total 42.

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, 37 out of 100, up to 11 more on the total

Why it scored 37: The docs say each company gets a single API key shared by all its users, sent in a header. The site's `auth.md` says a key can be deleted in the console, and the key page says to ask an administrator for a reset. No scopes (12 of 30). No read-only mode or per-key limits. The API mostly reads, writes are limited to webhooks and event enrolments, and auto-refill has an optional cap (5 of 20). Research scrapes web pages and the LinkedIn post enrichments return third-party text. No prompt-injection guidance was found in the docs (2 of 15). Balance and aggregation endpoints, per-call credit reporting, correlation IDs and last-active times for users. No per-call log was found (8 of 15). The privacy policy states SOC 2, ISO 27001 and ISO 27701. No security.txt, disclosure policy or bug bounty was found, and the security FAQ PDF went unread (10 of 20). Total 37.

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). Credit pack prices and per-operation credit costs are public without a login (20). The pricing page and the site's own `pricing.md` disagree on two packs, which is recorded as a deduction and not here. Free trial of 100 credits for 90 days. No page read asks for a card at sign-up, and the auto-refill guide treats a payment method as something added later (20). The vendor's `auth.md` says registration needs a person and there is no client-registration endpoint (0). Total 40.

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. Maintenance & community, 28 out of 100, up to 6.3 more on the total

Why it scored 28: The last dated API change found is v2 general availability on 2 September 2026, 37 days before the check (20 of 30). No dated changelog, so three entries in 90 days could not be shown (0). Support by email and by a shared Slack channel for customers that have one, with no public changelog or forum (5 of 15). No official REST SDK found. The repository's `server.json` names `ai.explorium/mcp-explorium`, and our registry lookup timed out (0). The `mcp-explorium` repository is MIT, with its last commit on 22 January 2026 and no CI workflow in the tree (3 of 10). Total 28.

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.

## 5. Agent ergonomics, 63 out of 100, up to 6 more on the total

Why it scored 63: The MCP v2 server has 11 tools (15), and the statistics tools are free for sizing an audience before a paid fetch (2 added back), 17 of 25. `page` and `page_size` up to 500, a `next_cursor` mode with no limit, and filters with autocomplete (20). Errors carry a `correlation_id`, 422 names the failing field, and Research returns failed rows with an `_error` field. Error bodies have no stable code (15 of 20). No idempotency keys. Retry guidance covers 429 and 500. MCP tool annotations were not read because we did not connect (6 of 20). No official REST SDK found in the docs index. Enrichment needs a match or fetch call first, and five filters need an autocomplete call first (5 of 15). Total 63.

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.

## 6. Schema & documentation, 76 out of 100, up to 3.9 more on the total

Why it scored 76: Public OpenAPI 3.1 file with 74 v2 and 67 v1 operations (25). llms.txt and a Markdown twin of every docs page (10). The spec's v2 operations have summaries and no descriptions. The docs pages and the 11 MCP tool descriptions say what each call is for and what to call first (12 of 20). Typed request schemas with enums and item limits, but 225 of 1,472 schema properties carry a description, and Research takes a free-form `output_schema` (11 of 15). Docs pages have request and response examples. The spec documents only 422 as an error, and the error guide lists Partner ID header messages that don't match the `api_key` scheme (10 of 15). Versions live in the path with a migration guide and a full v2 change list. No dated changelog was found (8 of 15). Total 76.

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.

## 7. Transparency & trust, 59 out of 100, up to 3.6 more on the total

Made of editorial 49, provenance 68.

Why it scored 59: Closed service. The Explorium Terms of Use (updated 14 June 2026) cover the Platform, API and data, and let Explorium change or end the service without notice (14 of 30). The privacy policy (updated 28 June 2026) sets out controller and processor roles, publishes 2025 request counts and links an opt-out page. Retention has no periods, and no DPA was found on the pages read (16 of 30). The v1 timeline gives about six and twelve months from 2 September 2026, marked indicative. Website traffic enrichment is slated for removal with no date (13 of 20). Processing in Israel, the United States and the EU is stated. No sub-processor list was found (6 of 20). Total 49.

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: explorium.ai, registered 2018-08-16 (8 years) (11 of 15)
- Terms of service: read, states 6 of the 7 things a reader expects, and has 3 clauses that cost points (3.1 of 10)
- Privacy policy: read, states 7 of the 8 things a reader expects (9.3 of 10)
- Status page: not found (0 of 10)
- security.txt: not found (0 of 10)

## Deductions

Each comes off the total. A fixed and documented problem counts for less at the next check.

- On 9 October 2026 the site's machine-readable `pricing.md` (dated 26 August 2026) lists Starter at $99.99 for 2,500 credits and Growth at 25,000 credits, while the pricing page it names as canonical lists $149.99 for 5,000 and 30,000. The site's `auth.md` and server card also send agents to the MCP server the docs call deprecated. A misleading published claim, 2 points (https://www.explorium.ai/pricing.md, https://www.explorium.ai/pricing/)

## 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: https://www.explorium.ai/credit-details/, the opt-out page and the security FAQ PDF on info.explorium.ai. We stopped asking the site for pages once we read that its terms bar automated data collection, and kept to its published agent files
- The home, pricing, data security, privacy, terms and MCP pages were fetched before the terms were read. robots.txt allows them and carries `ai-input=yes`
- unchecked: whether a status page exists. None is linked, and status.explorium.ai did not answer
- unchecked: the MCP registry entry. One lookup of registry.modelcontextprotocol.io timed out
- unchecked: the MCP v2 tool schemas and annotations. We did not connect to the server or call the API
- Whether the free trial needs a card. No page read says so
- Which price table is current for the Starter and Growth packs
- Whether a company can hold more than one key. The docs say one, and `auth.md` describes generating and deleting keys
- No SLA document, DPA, sub-processor list or SOC 2 report was found on the pages read
- The lead was right on the vendor, API and MCP server. The legal entity is Explorium Ltd., and the current MCP host is mcp-v2.explorium.ai

## Weaknesses

- No status page was found, and no SLA is published
- One API key per company, shared by all users, with no scopes or read-only mode
- The site's `pricing.md` and its pricing page give different prices for the Starter and Growth packs
- The terms of use bar benchmarking and automated data collection, and allow service changes without notice
- No dated changelog and no official REST SDK found in the docs index

## 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 the key in the `api_key` header to `https://api.explorium.ai` and use `/v2` paths. v1 is deprecated
- Point MCP clients at `https://mcp-v2.explorium.ai/mcp`. The site's agent files still name the v1 server at `mcp.explorium.ai`
- Count each entity in a batch as one query against the 200 a minute limit, so 50 IDs in one call spend 50
- Call the statistics endpoint first to size an audience for free. Fetch costs 1 credit a result, or 2 with the Bombora intent filter
- Call `/v2/autocomplete` before filtering on category, tech stack or job title, and never mix two category types in one request

## 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.