faq · the mcp server

The MCP server, answered in full.

Written for the person who has to defend a company master to people who did not build it. Quote any of it.

The same pipeline reached over the Model Context Protocol, and the questions that only matter once a model is holding the credential: what it can spend, what it can delete, what it can mint, and what it gets back when the answer is genuinely ambiguous.
questions on this subject, each answered in full
5
pages these answers are worked out on, all linked below
2
questions across the whole FAQ
74
Self-serviceCreate your workspace online and verify your email to start matching company records. Free starts with 300 credits and no card. Paid monthly plans are available in workspace Billing; VAT is added where applicable. Usage is tracked without automatic overage charges. Trust and security
Elsewhere in the FAQ
5 questions

Everything we are asked about the MCP server and what an agent can do with it

Open the ones you need. Each answer is written to be read on its own, so a figure arrives with the population behind it — the fixture it was measured on and the rows it covers — and still holds when you paste it into an email.

What is the MCP server?

The same pipeline exposed to agents as eleven tools over the Model Context Protocol, on local stdio or a remote URL. Two of the eleven are billable — resolving a company and comparing two records — and nine are free: read an entity, read a crosswalk, discover enrichment fields, search, redeem a decision receipt, read usage, and the three review-queue tools. It delegates to the same application services as the HTTP API, so a resolve over MCP is the same resolve, at the same price, against the same rate-limit bucket. Limits are shared rather than doubled. Deliberately absent: batch, catalogue export, erasure and provisioning, all of which stay on the HTTP surface.

Do I need OAuth to connect an agent?

No, and static bearer is the path to reach for first. The `rk_` API key you create in your Entity Bind workspace authenticates the remote MCP transport unchanged as an `Authorization: Bearer` header — the option credential vaults call `static_bearer`. OAuth exists, with PKCE S256 required, one issuable scope and operator-registered clients, but there is an integration gap to know about before you plan around it: the listener publishes no RFC 9728 protected-resource metadata and answers an unauthenticated tool call with a tool error rather than a 401 challenge. A client that starts its OAuth flow from a 401 will never start it. Discovery-driven clients work only behind a shared origin.

Can an agent spend money without us noticing?

Every billable tool returns a `usage` block — credits charged, credits remaining, deep attempts remaining, plan, and whether billing is enforced — and that block is the only place an agent can learn what a call cost, because a tool call has no response headers to read. So an agent can audit its own spend rather than be told it is cheap. The credential also caps depth before the cascade runs, so a key pinned to `probabilistic` cannot reach agentic research by choosing this surface. And the abstention rule holds here too: Free-tier or not, an `unresolved` costs zero credits, so an agent asking a question nobody can answer is not a bill.

Can an agent delete data or create credentials?

No, structurally rather than by policy. There is no erasure tool and no provisioning tool on the MCP surface, and an admin-scoped key is refused outright before a caller object is even constructed — so the credential that can mint credentials is unreachable by a model. Tenancy is derived per call from the credential and is never a request parameter; every repository method requires a tenant id as a keyword argument with no default; and a cross-tenant read reports 404 rather than 403. An erasure obligation is discharged by a person who can be asked why, which is a support conversation rather than a step in an agent's plan.

What does an agent get back when the answer is ambiguous?

An `unresolved`, with everything it needs to decide what to do next: the ranked shortlist with calibrated per-candidate probabilities, a review id, a decision id, and four flags that carry different instructions. `depth_capped` means you stopped this and a deeper call may resolve it. `escalation_unavailable` means a dependency failed and a retry is worth trying. `more_input_needed` means the paid stages could not separate the shortlist and retrying deeper will not change it — send a domain, a registration number or an LEI instead. `no_identifying_signal` means the fields normalised to nothing, and it is the only one the agent can fix by itself.

When the answer depends on what your own rows look like, it has to be measured on your file.

Start free
where the answers come from

The pages behind these answers

Each answer above is the short version. These pages carry the working: the tables, the payloads, the coverage rows and the caveats an answer can only point at.

evidence basis

Internal fixtures only. The historical 2026-08-29 per-tier recording covers 317 GB companies with identifier-rich arrivals seeding the catalogue first; the context tier includes country and registered-town prose. Its legacy replay has no full-prompt-verified calls and cannot certify current calibration. The September 5 CI reports cover 1,176 labelled pairs and 705 records over 250 companies using offline stubs. These are not independent customer holdouts or live production validation; the 99% minimum-input product target remains unmet. Scope is company and organisation identity only — not people, vessels, bank-account ownership, sanctions or emissions. Results may not be used for eligibility decisions about individuals, including employment, credit and tenancy.

Every figure, its population and what it does not show →

who this is for

Built for one job. Wrong for several others.

built for

Teams with a company master they have to defend — an MDM or stewardship queue, a CRM after a migration or a merger, a supplier file before a payment run, or counterparty onboarding that has to survive an audit.

wrong for

Buying breadth as the product: we hold a fraction of an incumbent’s records and are not building a global company graph. Entity Bind resolves companies and organisations only. It does not resolve people, vessels, bank-account ownership, sanctions exposure, emissions or geolocation, and its results may not be used for eligibility decisions about individuals, including employment, credit and tenancy.

the rest of the faq

74 questions, in 8 groups

Every question this site answers sits in one of these groups. If you are not sure which one covers yours, the index carries all 74 in a single page you can search in the browser.

All 74 questions in one page →

If none of these groups covers your question, send the file it is about — or write to hello@entitybind.com and we will answer it here.

Talk to us
the ask

Start with your own company records.

Every answer above is the general case. Create your Free workspace and inspect your own company CSV to see which rows match and which need review. Contact us for an assisted audit of existing matches. We write nothing to your systems.

300 credits. No card.

For a guided review of your file, explore the Merge Safety Sprint →