SanctionsKit developer MCP
Measured conclusion: Alive, not deep-tested. L2 outcome: not_attempted.
Sanctions API docs and request validation, with account-linked synthetic sandbox testing.
| Author | io.github.SanctionsKit |
|---|---|
| Access | remote |
| Publisher key required | No |
| Measured state | Alive, not deep-tested |
| L1 liveness | alive |
| L1 latency | 2157 ms |
| Last measured | 2026-10-26 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"SanctionsKit developer MCP": {
"url": "https://www.sanctionskit.com/mcp",
"transport": "streamable-http"
}
}
}
Measured tools (9)
search_docsread-onlyFind current integration documentation and guides by keyword. Returns document slugs for get_doc. Public; no account needed.
Parameters:
query(required) — stringlimit— integer
Hints: read-only yes · destructive no · idempotent yes · open-world no
get_docread-onlyRead a document returned by search_docs, including code examples and error handling. Uses a fixed local document catalog; does not fetch arbitrary URLs.
Parameters:
slug(required) — string
Hints: read-only yes · destructive no · idempotent yes · open-world no
get_api_schemaread-onlyWithout 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.
Parameters:
path— stringmethod— string
Hints: read-only yes · destructive no · idempotent yes · open-world no
validate_screening_requestread-onlyValidate 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.
Parameters:
request(required)
Hints: read-only yes · destructive no · idempotent yes · open-world no
list_sourcesread-onlyRead 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.
Parameters:
limit— integerquery— stringoffset— integer
Hints: read-only yes · destructive no · idempotent yes · open-world no
run_sandbox_screeningSubmit 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.
Parameters:
request(required) — objectidempotencyKey(required) — stringsynthetic(required) — boolean
Hints: read-only no · destructive no · idempotent yes · open-world no
get_screening_resultRetrieve 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.
Parameters:
id(required) — string
Hints: read-only no · destructive no · idempotent yes · open-world no
get_usageread-onlyRead the connected sandbox workspace allowance, completed subjects and pending reservations.
Hints: read-only yes · destructive no · idempotent yes · open-world no
get_profileread-onlyIdentify the sandbox profile represented by the authenticated connection. Takes no user or workspace selector.
Hints: read-only yes · destructive no · idempotent yes · open-world no
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.