Skip to main content
Glama
toolgate

toolgate

toolgate

English · Português

A control panel for the tools an AI assistant can use. You decide who can use each tool, passwords stay encrypted, and every call is logged so you can check later who did what.

toolgate

What you can do

  • Chat with the tools. Ask "which grants are overdue in MS?" and the chat picks the right tool, asks for anything missing and explains the result. Conversations are saved.

  • Control who uses what. Each role (admin, analyst, auditor) only sees the tools it is allowed to call.

  • Add new tools without touching code. Register an HTTP endpoint in the panel; it only goes live after another person approves it.

  • Keep passwords and tokens safe. They're encrypted and never shown back on screen.

  • Audit everything. Each call becomes a log entry with personal data (tax ids, emails, cards) already masked. Entries are chained by hash, so you can tell if someone edited an old one.

Works with Claude Desktop or any MCP client, plus the web panel.

Related MCP server: mcpgate

Running it

git clone https://github.com/murilo-bassan/mcp-tool-gateway.git
cd mcp-tool-gateway
pip install -r requirements-dev.txt

python -m pytest                              # tests
python scripts/demo_traffic.py                # optional: sample activity
python -m uvicorn web.app:app --port 8600     # http://localhost:8600

Test logins: admin/admin, analyst/analyst and auditor/auditor. Also runs with docker compose up --build.

To use it in Claude Desktop, copy docs/claude_desktop_config.example.json. To try it from the terminal:

python scripts/mcp_call.py list
python scripts/mcp_call.py call invoices.validate_tax_id '{"tax_id": "11.222.333/0001-81"}'

The chat works without any model. To use an LLM, set GATEWAY_LLM_API_KEY, GATEWAY_LLM_BASE_URL and GATEWAY_LLM_MODEL (any OpenAI-compatible API).

How it works

Every call, whether it comes from Claude Desktop, the panel or another system, goes through the same path: check permission, apply the rate limit, validate the arguments, run, log. No entry point skips those steps.

gateway/
  executor.py   the single path for every call
  access.py     users, roles and permissions
  registry.py   tools registered from the panel
  audit.py      hash-chained log
  masking.py    personal data masking
  chat.py       the chat
  domains/      sample tools (invoices and grants)
server.py       MCP server
web/            web panel

Design decisions are in docs/adr and the security model in docs/security.md.

Screens

Console

Audit log

Registered tools

Permissions

Stack: Python, FastAPI, MCP, SQLite, Docker

All data is made up. MIT license.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables centralized proxy and orchestration of MCP servers, providing unified tool discovery, authentication, and secure request routing. It adds a human-in-the-loop approval gate for high-risk actions and audit logging.
      Apache 2.0
    • A
      license
      Not graded
      quality
      B
      maintenance
      Exposes any number of upstream MCP servers (stdio subprocesses or Streamable HTTP endpoints) as one MCP server for LLM agents, with namespaced tool names so servers cannot shadow each other. Every tool call passes centralized OAuth 2.1 bearer validation, per-client tool RBAC, rate limits, JSON Schema argument checks, a hash-chained audit log, and tool-definition pinning that quarantines changed tools until an operator approves them.
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Aggregates multiple stdio or Streamable HTTP MCP servers behind a single OAuth-secured endpoint, applying per-client tool RBAC, rate limits, schema validation, audit logging, and tool-definition pinning before forwarding tool calls.
      MIT