Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@LittleSis MCP find connections between Goldman Sachs board members and government officials"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP (Model Context Protocol) server that provides access to the LittleSis API for tracking corporate power and accountability relationships.
To install littlesis-mcp for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @code-rabi/littlesis-mcp --client claudeThis MCP server implements all major LittleSis API endpoints:
get_entity - Get detailed information about a specific entity
get_entities - Get multiple entities at once (up to 300)
search_entities - Search for entities by name with filtering
get_entity_extensions - Get entity types/classifications
get_entity_relationships - Get all relationships for an entity
get_entity_connections - Get connected entities
get_entity_lists - Get lists an entity appears on
get_relationship - Get detailed relationship information
Related MCP server: mcp-edgar
{
"mcpServers": {
"littlesis": {
"command": "node",
"args": ["dist/index.js"],
"cwd": "/path/to/littlesis-mcp"
}
}
}All data accessed through this MCP server is from LittleSis and is licensed under CC BY-SA 4.0.
LittleSis is a free database of who-knows-who at the heights of business and government. It tracks the revolving door between business and government, political donations, and more.
MIT License - see LICENSE file for details.
Get information about multiple entities at once (up to 300 entities per request)
Inputs: ids (required).
Get detailed information about a specific entity (person or organization) from LittleSis by ID
Inputs: id (required).
Get other entities that this entity has relationships with
Inputs: id (required), category_id, page.
Get the types/extensions associated with an entity (Person, Organization, Business, etc.)
Inputs: id (required), details.
Get the lists that an entity appears on (e.g., Fortune 1000, lobbying lists)
Inputs: id (required).
Get all relationships this entity has with other entities
Inputs: id (required), category_id, sort, page.
Get detailed information about a specific relationship between two entities
Inputs: id (required).
Search for entities by name. Results are ranked by number of relationships.
Inputs: q (required), page, regions, tags.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 8 tools
Every tool has a clearly distinct purpose with no ambiguity. The tools are well-segmented: get_entity for single entity details, get_entities for batch retrieval, get_entity_connections for related entities, get_entity_extensions for entity types, get_entity_lists for list membership, get_entity_relationships for relationship details, get_relationship for specific relationship info, and search_entities for name-based searching. There is no overlap in functionality.
All tools follow a consistent verb_noun pattern with 'get_' or 'search_' prefixes and snake_case naming. The naming is highly predictable: get_entity, get_entities, get_entity_connections, get_entity_extensions, get_entity_lists, get_entity_relationships, get_relationship, and search_entities. There are no deviations or mixed conventions.
The 8 tools are well-scoped for the LittleSis domain, which focuses on entity and relationship data. Each tool earns its place by covering distinct aspects like entity retrieval, relationship details, extensions, lists, and searching. This count is typical for a data-focused API and avoids being too thin or heavy.
The tool set provides comprehensive coverage for querying entities and relationships, including CRUD-like operations for reading (get, search) and exploring connections. Minor gaps exist, such as no explicit tools for creating, updating, or deleting data, but these are likely intentional for a read-only API, and agents can work around this with the available tools for full query workflows.
Extract structured SEC EDGAR company facts, CIK lookups, and regulatory financial filings.
Find a company's parent chain and subsidiaries from GLEIF LEI data. $0.02/call via x402.
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
Korean company facts in English for AI agents: ~830 KOSPI-listed companies (DART profiles, KRW financials, recent filings) and ~110,000 corporate public procurement suppliers (12-month KONEPS contract awards), plus live National Tax Service business status checks. 4 tools, keyless, read-only.
