MCP.Market

mcp-broker MCP server

by NavinAgrawal·io.github.NavinAgrawal/mcp-broker·v1.4.1·5 stars

Local MCP broker that exposes one compact entry for many upstream servers.

A94/100grade A
What users say
No reviews yet
Be the first
Safety scan
A94/100

full report

Adoption
Growing

5 stars71 downloads/wk

Reviews

Write one

Nobody has reviewed mcp-broker yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

mcp-broker tools

No tool declarations could be read from the package source. They show once the server is installed.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan39 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 7 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10
Overall 94/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How mcp-broker compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
94/100
higher than 96% of 48,255 servers
GitHub stars
5
more than 83% of 28,688 servers
Downloads a week
71
more than 54% of 12,191 servers with a package

Install mcp-broker in Claude Code, Cursor or VS Code

claude mcp add mcp-broker -- uvx mcp-broker
Add to Cursor

What the publisher says

From the mcp-broker repository's README, as published. We do not edit it. Read it on GitHub

mcp-broker

<!-- mcp-name: io.github.doricstack/mcp-broker -->

mcp-broker is a local Model Context Protocol process broker for MCP clients.

Think PgBouncer for MCP: one stable local endpoint in front of many upstream MCP servers. The broker owns upstream startup, reuse, cleanup, profile exposure, status, and safe tool routing.

The core idea is simple: do not make every agent session load every upstream tool definition before the user asks a task.

Why this exists

AI coding sessions with many MCP servers tend to accumulate the same problems:

  • every client config repeats the same MCP server list
  • every new session can start duplicate upstream processes
  • OAuth, browser state, local files, and database handles spread across tools
  • raw tool lists consume context before the task begins
  • hosted connector caches can duplicate local MCP tools
  • orphaned MCP processes survive after client sessions exit

mcp-broker puts a small broker facade in front of those upstreams. It is not a hosted workflow builder; it is local infrastructure for keeping MCP clients small, predictable, and under one config contract.

Client profile
        |
        | one local MCP entry
        v
  mcp-broker-client
        |
        | Unix socket
        v
  mcp-broker-daemon
        |
        | profile gates, namespace routing, status, cleanup
        v
  upstream MCP servers

The client sees a small set of broker tools:

broker_search_tools
broker_describe_tool
broker_call_tool
broker_status
broker_close_session

The upstream MCPs still exist. They are discovered and called through the broker when a task needs them.

Measured context reduction

On 2026-05-24, the measured Codex setup went from many raw MCP and hosted app tool definitions to one broker facade plus a pruned codex_apps cache.

The 92.94% number is a tool-definition count reduction. The 83.65% number is a token reduction for canonical serialized tool payloads measured with tiktoken o200k_base.

See docs/context-reduction-measurement.md for evidence and caveats.

What it does

  • Runs one local broker daemon over a Unix socket.
  • Exposes one lightweight stdio client shim to MCP clients.
  • Starts upstream MCP servers on demand.
  • Reuses shared upstreams across sessions when configured.
  • Isolates per-session upstreams when state must not be shared.
  • Maps upstream tools into stable namespaces.
  • Exposes compact search, describe, call, status, and caller-bound session-close tools.
  • Enforces profile-level tool budgets and exposure gates.
  • Blocks mutating upstream exposure unless a profile allowlist grants it.
  • Stores runtime state under $HOME/mcp/mcp-broker, outside the repo.
  • Renders MCP client config entries with dry-run, backup, and rollback.
  • Provides LaunchAgent install and uninstall flows for macOS.

Core differentiators:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

mcp-broker: common questions

Is mcp-broker MCP server safe?
Yes, by our scan: it is graded A (94/100). Read the mcp-broker safety report
How do I install mcp-broker?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does mcp-broker need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is mcp-broker maintained?
The last commit was 45 days ago (2026-09-20). The latest release is v1.4.1.
How does mcp-broker compare with other MCP servers?
safety score 94/100 (higher than 96% of 48,255 servers); github stars 5 (more than 83% of 28,688 servers); downloads a week 71 (more than 54% of 12,191 servers with a package). Full comparison.