Skip to main content
Glama
Brian20040323

MCP Knowledge Bridge

MCP Knowledge Bridge

Python Version License: MIT

An educational, hand-written implementation of a useful MCP subset. Version 0.3.0 supports the 2025-11-25 protocol version over stdio with tools, resources, prompts, ping, initialization lifecycle enforcement, and JSON-RPC errors. It is intentionally small and is not a complete MCP SDK or production gateway.

Install and run

python -m pip install -e ".[dev]"
python -m examples.demo_protocol
python -m mcp_bridge.server

The stable MCP stdio transport uses one UTF-8 JSON-RPC message per line. Each message must be on a single line; this project does not use Content-Length framing.

Installed console script:

mcp-knowledge-bridge

Cursor MCP config

{
  "mcpServers": {
    "knowledge-bridge": {
      "command": "python",
      "args": ["-m", "mcp_bridge.server"],
      "cwd": "/absolute/path/to/mcp-knowledge-bridge"
    }
  }
}

Related MCP server: Alcove

Custom REST companion

mcp_bridge.http_server is a custom authenticated REST companion. It is not MCP Streamable HTTP, does not implement MCP over HTTP, and does not implement OAuth. It exposes convenience endpoints for this repository's tools and resources.

Startup requires an explicit MCP_BRIDGE_TOKEN; there is no default token and query-string tokens are rejected. /health remains public and does not reveal the token.

export MCP_BRIDGE_TOKEN="replace-with-a-secret"
mcp-knowledge-bridge-rest
curl -H "Authorization: Bearer replace-with-a-secret" http://127.0.0.1:8765/tools

On PowerShell, set the environment variable with:

$env:MCP_BRIDGE_TOKEN = "replace-with-a-secret"

Scope

The implemented MCP surface is initialize, notifications/initialized, ping, tools/list, tools/call, resources/list, resources/read, prompts/list, and prompts/get. Protocol negotiation currently accepts only 2025-11-25. The in-process client creates an independent server session for tests and simple adapters.

The repository does not claim support for sampling, roots, elicitation, subscriptions, completion, logging, tasks, Streamable HTTP, or other unimplemented MCP features.

Development

python -m ruff check .
python -m pytest --cov=mcp_bridge --cov-report=term-missing

MIT © Brian20040323

Install Server
A
license - permissive license
B
quality
B
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    A
    quality
    A
    maintenance
    Cross-agent memory bridge for AI coding assistants. Persistent knowledge graph shared across 10 IDEs (Cursor, Windsurf, Claude Code, Codex, Copilot, Kiro, Antigravity, OpenCode, Trae, Gemini CLI) via MCP. 22 tools including team collaboration, auto-cleanup, mini-skills, session management, and workspace sync. 100% local, zero API keys required.
    Last updated
    9
    1,717
    594
    Apache 2.0
  • A
    license
    A
    quality
    B
    maintenance
    MCP server that gives AI coding agents on-demand access to private project docs via BM25 ranked search. One setup for Claude Code, Cursor, Codex, Gemini CLI, and more. Docs stay private, never in public repos.
    Last updated
    15
    15
    Apache 2.0
  • A
    license
    A
    quality
    C
    maintenance
    Universal MCP knowledge server for LLM agents, powered by local RAG, providing domain-specific best practices and playbooks across software engineering, marketing, video editing, and other knowledge areas.
    Last updated
    3
    MIT

View all related MCP servers

Related MCP Connectors

  • Local-first RAG engine with MCP server for AI agent integration.

  • User-owned memory for AI agents, Copilot, Claude, IDEs, CLIs, and chat apps over remote MCP.

  • Your memory, everywhere AI goes. Build knowledge once, access it via MCP anywhere.

View all MCP Connectors

Latest Blog Posts

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/Brian20040323/mcp-knowledge-bridge'

If you have feedback or need assistance with the MCP directory API, please join our Discord server