Developer Context Agent
Provides integration with OpenAI's API for using GPT models as the language model backend for the agent.
Click on "Install 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., "@Developer Context Agentexplain how authentication works in my project"
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.
developer-context-agent
Token-efficient codebase context for AI assistants.
Indexes your repo locally, ranks relevant files with hybrid retrieval, and returns token-budgeted context packs via MCP — no LLM required in this package.
Works with Cursor, Claude Desktop, Windsurf, and any Model Context Protocol client.
The host LLM (Cursor, Claude, etc.) does the reasoning.
This agent finds, ranks, and compresses codebase context.
Install
npm install -g developer-context-agentOr use without installing:
npx developer-context-agent --helpRequirements: Node.js 20+
Related MCP server: token-savior
Quick start
cd your-project
context-agent index
context-agent pack --task "how does auth work"Use with Cursor
Add .cursor/mcp.json in your project:
{
"mcpServers": {
"context-agent": {
"command": "npx",
"args": ["-y", "developer-context-agent", "mcp"],
"env": {
"REPO_PATH": "${workspaceFolder}"
}
}
}
}Restart Cursor, enable the MCP server in Settings → MCP, then chat as usual. The model can call get_context_pack before reading files.
Recommended Cursor rule (.cursor/rules/context-agent.mdc):
Before reading large files or searching the codebase manually, use context-agent MCP tools:
1. get_context_pack for the user's question
2. find_files / search_symbols only if more detail is neededUse with Claude Desktop / other MCP clients
{
"mcpServers": {
"context-agent": {
"command": "npx",
"args": ["-y", "developer-context-agent", "mcp"],
"env": {
"REPO_PATH": "/absolute/path/to/your/repo"
}
}
}
}How it works
You ask in Cursor chat
↓
Host LLM calls get_context_pack("auth middleware")
↓
Agent: grep + symbols + import graph (+ optional vectors)
↓
Returns small markdown context pack (token-budgeted)
↓
Host LLM answers using that contextLocal index is stored in .context-agent/ inside your project (SQLite). Nothing is sent to a cloud service by this package.
CLI
Command | Description |
| Start MCP server (stdio) |
| Build or refresh local index |
| Show index metadata |
| Print context pack to stdout |
Examples:
context-agent index --repo .
context-agent status --repo .
context-agent pack --task "explain hybrid retrieval" --max-tokens 6000MCP tools
Tool | Description |
| Primary tool — token-budgeted context for a task |
| Rank files by relevance (grep + symbols + vectors) |
| TypeScript/JavaScript symbol search |
| Sandboxed ripgrep |
| Sandboxed file read (optional line range) |
| Build or refresh local index |
| Index health and chunk count |
Configuration
Environment variables (optional):
Variable | Default | Description |
|
| Default repository path |
|
| Default context pack token budget |
|
| Ollama API for embeddings |
|
| Embedding model |
| — | Comma-separated repo path allowlist |
Optional: semantic search with Ollama
Hybrid retrieval works without Ollama (grep + symbols + import graph).
For vector similarity search:
ollama pull nomic-embed-text
context-agent indexDevelopment
Clone and work on the source repo:
git clone https://github.com/SinuxDev/developer-context-agent.git
cd developer-context-agent
npm install
npm test
npm run context-agent -- index --repo .
npm run mcpLegacy HTTP server
An optional Fastify API (POST /chat, POST /runs) with Postgres/Redis is still in the codebase for supervised runs. It is not required for the MCP agent.
npm run docker:up
npm run db:migrate
npm run devSee docs/IDE_BRIDGE.md for HTTP API details.
Links
Repository: https://github.com/SinuxDev/developer-context-agent
Issues: https://github.com/SinuxDev/developer-context-agent/issues
License
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/SinuxDev/developer-context-agent'
If you have feedback or need assistance with the MCP directory API, please join our Discord server