Sanctions API docs and request validation, with account-linked synthetic sandbox testing.
Scored across 9 tools
Each tool targets a distinct action: docs discovery (search_docs/get_doc), schema introspection (get_api_schema), validation vs. execution (validate_screening_request vs run_sandbox_screening), and evidence/workspace reads (get_screening_result, get_usage, list_sources, get_profile). Minor overlap between get_api_schema and get_doc since both surface documentation, but the descriptions clearly separate schema retrieval from doc reading.
All nine tools follow a consistent snake_case verb_noun pattern (get_*, list_*, run_*, search_*, validate_*). Verbs are used predictably: get_* for reads, list_* for enumeration, run_* for submission, validate_* for checks.
Nine tools is well-scoped for a sandbox developer kit covering documentation, schema, validation, submission, and result retrieval. Every tool has a clear role with no filler.
The core developer workflow is covered end-to-end: search docs, read docs, inspect schema, validate a request, run a sandbox screening, and retrieve evidence/usage. Minor gaps exist around screening lifecycle management such as listing past screenings or cancelling/reviewing an open case, which the descriptions hint at but no tool exposes.
Without path, list consumer REST operations. With a path such as /screenings and lowercase method, retrieve its OpenAPI request, response, examples and referenced schemas. Describes REST capabilities; MCP account tools are sandbox only.
Inputs: path, method. Returns: data
Read a document returned by search_docs, including code examples and error handling. Uses a fixed local document catalog; does not fetch arbitrary URLs.
Inputs: slug (required). Returns: data
Identify the sandbox profile represented by the authenticated connection. Takes no user or workspace selector.
Inputs: no named parameters. Returns: id, name, email, nickname
Retrieve retained evidence by screening ID from the connected sandbox workspace. An expired result is an error. Preserve coverage, versions, warnings and potential-match review requirements.
Inputs: id (required). Returns: data
Read the connected sandbox workspace allowance, completed subjects and pending reservations.
Inputs: no named parameters. Returns: data
Read current source metadata and qualification from the connected sandbox workspace, with bounded pagination. Catalog/production source availability does not enable live MCP screenings; sandbox screening uses sandbox@1.
Inputs: limit, query, offset. Returns: data
Submit invented data to sandbox@1. Requires synthetic=true and an idempotencyKey of 8–128 URL-safe characters, reused unchanged with the same request for retries. Retains screening evidence according to policy and may create a review case; consumes sandbox allowance, never paid production allowance. Cannot screen production or link counterparties.
Inputs: request (required), synthetic (required), idempotencyKey (required). Returns: data
Find current integration documentation and guides by keyword. Returns document slugs for get_doc. Public; no account needed.
Inputs: query (required), limit. Returns: data
Validate request structure against the runtime REST screening schema without submitting or retaining it. Does not check live source eligibility or grant clearance. Use synthetic development inputs.
Inputs: request (required). Returns: data
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Sanctions, PEP, watchlist, recall, business, and contract screening. Free tier, no auth required.
Sanctions Screening MCP — screen people, companies, vessels, and aircraft against the US…
Screen people & companies against 12 US sanctions & exclusion lists (OFAC, LEIE, SAM, Medicaid).
Screen banks, wires, sanctions, wallets and transfers before an agent moves money. Free tier.
Add one secure layer between your agents and this server.
