MCP server for sanctions screening and PEP checks via the OpenSanctions API.
Lets AI agents (Claude, Cursor, Windsurf, GPT) screen persons and companies against 320+ sanctions and PEP lists from OFAC, EU, UN, UK HMT, and more.
Disclaimer: This tool provides informational data only. It is not legal or compliance advice. Always verify matches with official sources before taking action.
Add to your MCP client config:
{
"mcpServers": {
"opensanctions": {
"command": "npx",
"args": ["-y", "opensanctions-mcp"],
"env": {
"OPENSANCTIONS_API_KEY": "your-key-here"
}
}
}
}Get a free API key at opensanctions.org/api.
Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
Cursor: Settings > MCP Servers
Windsurf: ~/.windsurf/config.json
Related MCP server: mcp-sanctions-check
Search the OpenSanctions database by name or keyword.
"Search for entities named Viktor Bout"
"Find companies related to Iran sanctions"Screen a person or company against sanctions and PEP lists using structured properties. This is the primary screening tool.
"Screen Viktor Bout, born 1967-01-13, Russian national, against sanctions lists"
"Check if Acme Corp is on any EU sanctions list"Fetch complete details for a specific entity, including relationships to other entities (companies, associates, family members).
"Get full details for entity NK-2Ciy8EG7jz1YHMGCxYLb25"List available sanctions and PEP datasets. No API key required.
"What sanctions lists are available?"
"Show me EU-related datasets"Get details about a specific dataset (publisher, entity count, last updated). No API key required.
"Tell me about the OFAC SDN list"Run a full compliance investigation in one call: match, fetch details, map relationships, and return structured data.
"Investigate Viktor Bout for sanctions exposure"
"Run a compliance check on Acme Corp, jurisdiction Belgium"Environment Variable | Required | Default | Description |
| Yes* | — | API key for the hosted OpenSanctions API. Get one at opensanctions.org/api. |
| No |
| API URL. Set to your self-hosted yente instance. |
| No |
| Dataset to screen against. |
| No |
| Max retries for failed API calls. |
| No | — | Set to any value to enable debug logging. |
*Not required for list_datasets, get_dataset, or when using a self-hosted yente instance without auth.
If you run your own yente instance, point the server at it:
{
"mcpServers": {
"opensanctions": {
"command": "npx",
"args": ["-y", "opensanctions-mcp"],
"env": {
"OPENSANCTIONS_API_URL": "http://localhost:8000"
}
}
}
}No API key needed for self-hosted yente.
git clone https://github.com/scka-de/opensanctions-mcp.git
cd opensanctions-mcp
npm install
npm test # run tests (fixtures, no API key needed)
npm run build # compile to dist/
npm run dev # run in dev mode
npm run lint # check code styleMIT
Get full details about a specific dataset: description, publisher, entity count, last updated, and coverage information. No API key required.
Use list_datasets first to find dataset names, then this tool for details.
Inputs: name (required).
Fetch complete details for a specific entity by ID, including all properties, dataset memberships, and relationships to other entities.
Use this after finding an entity via search or match to get the full picture: aliases, addresses, birth dates, related companies, family members, associates.
Relationships come from the OpenSanctions knowledge graph. Types include: ownershipOwner, familyRelative, associate, directorshipDirector, and more.
Inputs: entityId (required).
Run a multi-step compliance investigation on a person or company. This is the most powerful tool — it combines matching, entity details, and relationship traversal in one call.
Steps: (1) Match the name against sanctions/PEP lists, (2) Fetch full details and relationships for top matches, (3) Return structured data with scores, datasets, and connected entities.
Returns data only — no risk judgments. You (the AI) should interpret the scores, dataset memberships, and relationships to provide context to the user.
Requires both name and schema (Person/Company). Provide additional properties like birthDate or nationality for better match precision.
Inputs: name (required), schema (required), birthDate, nationality, +4 more.
List available sanctions and PEP datasets in OpenSanctions. No API key required.
Returns dataset names, titles, summaries, and entity counts. Use the optional query parameter to filter. Examples of datasets: "us_ofac_sdn" (US OFAC), "eu_fsf" (EU Financial Sanctions), "un_sc_sanctions" (UN Security Council), "gb_hmt_sanctions" (UK HMT).
Inputs: query.
Screen a person or company against sanctions and PEP (Politically Exposed Person) lists using structured properties.
This is the primary screening tool. Provide a schema type and properties for precise matching. The matching algorithm uses name comparison, birth dates, nationalities, and identifiers for scoring.
Scores: 0.0-1.0. Above 0.9 = very high confidence match. 0.7-0.9 = likely match, investigate further. Below 0.7 = possible but uncertain.
PEP = Politically Exposed Person (senior government officials, their families, close associates). PEP status appears in the "topics" property as "role.pep".
Inputs: schema (required), properties (required), dataset.
Search the OpenSanctions database by name or keyword. Returns matching entities ordered by relevance.
Use this for exploratory queries: "find entities named Goldman", "search for companies in Russia". For formal sanctions screening with confidence scores, use match_entity instead.
Results include entity type, datasets (which sanctions lists), and properties. For numeric match scores, use match_entity.
Inputs: query (required), schema, dataset, limit.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 6 tools
Each tool has a clearly distinct purpose with minimal overlap: list_datasets enumerates datasets, get_dataset retrieves dataset details, search_entities performs keyword searches, match_entity conducts structured screening with scores, get_entity fetches full entity details, and investigate_entity runs comprehensive investigations. The descriptions explicitly differentiate them, such as noting that search_entities is for exploratory queries while match_entity is for formal screening.
All tool names follow a consistent verb_noun pattern using snake_case: list_datasets, get_dataset, search_entities, match_entity, get_entity, and investigate_entity. This uniformity makes the tool set predictable and easy to navigate, with no deviations in naming conventions.
With 6 tools, the server is well-scoped for its domain of sanctions and PEP data access. Each tool serves a specific function in the workflow, from listing and getting datasets to searching, matching, and investigating entities, without being overly sparse or bloated.
The tool set provides complete coverage for the OpenSanctions domain, including dataset enumeration (list_datasets, get_dataset), entity discovery (search_entities, match_entity), detailed retrieval (get_entity), and advanced analysis (investigate_entity). There are no obvious gaps; agents can perform full workflows from initial screening to in-depth investigation.
OpenSanctions MCP — global sanctions and PEP data.
Sanctions Screening MCP — screen people, companies, vessels, and aircraft against the US…
sanctions.io MCP — wraps the sanctions.io Screening API (api.sanctions.io)
CompanyLens is a remote MCP server giving AI agents instant access to official company registry data across 19 jurisdictions in Europe, the Americas, and Asia-Pacific. Eighteen read-only tools let you search companies and people, look up officers and beneficial owners, map corporate networks through shared directors, screen names against the UK disqualified directors register, find every company at a registered address, and pull filing history — all from a single connector. Visit our website: https://companylens.io
