SEC Intelligence runs on your own machine — the client starts it, so there is no endpoint to ping. 94 installs a week from pypi. Last commit 7 Oct 2026.
SEC 10-K/10-Q/8-K search, RAG Q&A, comparison, and anomaly detection with citations.
Today is the operative word: we check SEC Intelligence every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add sec-intelligence-mcp -e 'GEMINI_API_KEY=<GEMINI_API_KEY>' -e 'QDRANT_URL=<QDRANT_URL>' -e 'LANGFUSE_SECRET_KEY=<LANGFUSE_SECRET_KEY>' -e 'LANGFUSE_PUBLIC_KEY=<LANGFUSE_PUBLIC_KEY>' -- uvx sec-intelligence-mcp
{
"mcpServers": {
"sec-intelligence-mcp": {
"command": "uvx",
"args": [
"sec-intelligence-mcp"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>",
"LANGFUSE_PUBLIC_KEY": "<LANGFUSE_PUBLIC_KEY>",
"LANGFUSE_SECRET_KEY": "<LANGFUSE_SECRET_KEY>",
"QDRANT_URL": "<QDRANT_URL>"
}
}
}
}
[mcp_servers.sec-intelligence-mcp]
command = "uvx"
args = ["sec-intelligence-mcp"]
env = { GEMINI_API_KEY = "<GEMINI_API_KEY>", QDRANT_URL = "<QDRANT_URL>", LANGFUSE_SECRET_KEY = "<LANGFUSE_SECRET_KEY>", LANGFUSE_PUBLIC_KEY = "<LANGFUSE_PUBLIC_KEY>" }
{
"mcpServers": {
"sec-intelligence-mcp": {
"command": "uvx",
"args": [
"sec-intelligence-mcp"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>",
"LANGFUSE_PUBLIC_KEY": "<LANGFUSE_PUBLIC_KEY>",
"LANGFUSE_SECRET_KEY": "<LANGFUSE_SECRET_KEY>",
"QDRANT_URL": "<QDRANT_URL>"
}
}
}
}
{
"servers": {
"sec-intelligence-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"sec-intelligence-mcp"
],
"env": {
"GEMINI_API_KEY": "<GEMINI_API_KEY>",
"LANGFUSE_PUBLIC_KEY": "<LANGFUSE_PUBLIC_KEY>",
"LANGFUSE_SECRET_KEY": "<LANGFUSE_SECRET_KEY>",
"QDRANT_URL": "<QDRANT_URL>"
}
}
}
}
Put your own values in place of
<GEMINI_API_KEY> (Google Gemini API key (free tier). Get one at https://aistudio.google.com/apikey), <QDRANT_URL> (Qdrant vector database URL, e.g. http://localhost:6333 for local Docker, or a Qdrant Cloud cluster URL), <LANGFUSE_SECRET_KEY> (LangFuse secret key for observability (free tier). Get one at https://cloud.langfuse.com), <LANGFUSE_PUBLIC_KEY> (LangFuse public key, paired with LANGFUSE_SECRET_KEY).
The author’s registry entry marks them as required.
Optional settings from the registry entry, left out of the block above:
QDRANT_API_KEY (Only needed for a hosted Qdrant Cloud instance; leave unset for local Qdrant), SEC_EDGAR_USER_AGENT (Identifying User-Agent for SEC EDGAR requests, e.g. "YourApp [email protected]"), EMBEDDING_MODEL (sentence-transformers model for embeddings), GEMINI_MODEL (Gemini model for answer generation).
Web search, scraping, RAG answers with citations, and translation as MCP tools.
MCP server for Milvus: collections, stats, search. Works with any instance.
Nigerian & Commonwealth legal reasoning, RAG search, contract analysis, and citation verification.
Build a RAG pipeline station by station and search your own documents with cited answers.
MCP RAG server with hybrid search, multi-KB support, and AI-powered chunk contextualization.
Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval
Search the web, generate AI responses, and create embeddings with real-time information
MCP server for Weaviate: collections, objects, GraphQL search. Works with any instance.
Answers built from our own checks of this server.