cursor-context-mcp
MCP server providing filesystem allowlist and pack-aware Qdrant RAG search. Enables reading files, listing directories, and performing filtered RAG searches with case and pack IDs.
README
cursor-context-mcp
MIT open-source MCP server: filesystem allowlist + pack-aware Qdrant RAG + optional demo Tool Gateway.
Not affiliated with Cursor. Works with Cursor, LM Studio, and any HTTP MCP host.
Features
| Tool | Description |
|---|---|
read_file |
Read UTF-8 text under configured allowlist roots |
list_directory |
List immediate children of an allowed directory |
search_files |
Stub (v0.1); use read_file + pack_rag_search |
pack_rag_search |
Qdrant scroll with mandatory case_id + pack_id filters |
vs @modelcontextprotocol/server-filesystem
| cursor-context-mcp | server-filesystem | |
|---|---|---|
| Path allowlist | Yes (CONTEXT_MCP_ALLOWED_ROOTS) |
Yes |
| Pack / case ACL RAG | Yes (pack_rag_search) |
No |
| Tool Gateway audit | Optional demo registry | No |
| Domain packs (legal/condo) | No — see Closed-source sibling below | No |
Install
From a standalone clone (repo root = this package):
git clone https://github.com/tomaxtoLuca/cursor-context-mcp.git && cd cursor-context-mcp
python -m venv .venv
source .venv/bin/activate # Linux/macOS
# .venv\Scripts\activate # Windows
pip install -r requirements.txt
Monorepo note: inside the tomaxto workspace, this package lives at mcp/cursor-context-mcp/.
Run
python scripts/acceptance_mcp.py # optional; Qdrant live test skips if down
python server.py # http://127.0.0.1:8780/mcp
Qdrant demo seed (optional):
docker run -p 6333:6333 qdrant/qdrant
python scripts/seed_demo.py
Cursor config
Add to .cursor/mcp.json. The key (cursor-context) is a display name you choose; port 8780 is the default for this server, not a universal MCP port.
{
"mcpServers": {
"cursor-context": {
"url": "http://127.0.0.1:8780/mcp"
}
}
}
Reload MCP in Cursor after starting the server.
Configuration
| Env | Default |
|---|---|
CONTEXT_MCP_ALLOWED_ROOTS |
config.yaml allowed_roots (. + fixtures) |
CONTEXT_MCP_HOST / PORT |
127.0.0.1 / 8780 |
CONTEXT_QDRANT_URL |
http://127.0.0.1:6333 |
CONTEXT_QDRANT_COLLECTION |
context_pack_demo |
CONTEXT_DEFAULT_PACK_ID |
demo-pack |
CONTEXT_GATEWAY_REGISTRY |
config/gateway_registry.example.json |
CONTEXT_GATEWAY_ENABLED |
true |
Copy .env.example to .env for local overrides.
Closed-source sibling
SIU production extensions (Legal / Condo / Studio packs, HubSpot LOB, siu-rag client) live in the private siu-context package (tomaxto monorepo). This open kernel does not include those adapters.
License
MIT — see LICENSE.
Last updated: 2026-06-18
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.