Jmunch Mcp

io.github.jgravellePublished by GitHub account jgravellev0.2.3Updated Oct 24, 2026

Transparent MCP proxy. Turns fat tool responses into queryable handles: 88-99% fewer tokens.

VerifiedSTDIODesktop onlyDeveloper ToolsAI & ML

Overview

AI-generated overview

A local proxy that wraps another MCP server and turns large tool responses into queryable handles, cutting token use by 88–99%.

What you can do
Wrap a single upstream MCP server and forward its tool calls, replacing bulky payloads with compact handles and summaries. Query handles with universal verbs: peek, slice, search, aggregate, describe, summarize and list handles. Route tabular results to a SQLite backend and JSON results to a JSON-tree backend for JSONPath slicing and search. Optionally run a gateway that applies the same handle-ification to OpenAI- or Anthropic-style HTTP API traffic. View read-only local metrics on forwarded calls and token savings.
When to use it
Useful when an assistant works through an MCP server whose tool results are large, such as issue, commit, scrape or search payloads, and you want to cut token cost and avoid paging through whole responses. Also relevant for apps calling OpenAI- or Anthropic-compatible APIs that want the same reduction without code changes.
Requirements
Runs locally as a Python package installed with pip; the gateway extra is needed for gateway mode. Requires an upstream MCP server to wrap and a config file, which the init command can generate from detected client configs. The gateway listens on a local HTTP port and is pointed at via base_url settings.
Before you install
It sits between your client and the upstream server and forwards every call, so it sees all tool traffic and results. Handles are persisted to a local database with a configurable TTL, so data from earlier sessions may remain readable. The gateway intercepts API requests and injects tools into them, which changes what the model sees.

Installation

In SourceWeft

  1. Open Jmunch Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

jmunch-mcp

Transparent MCP proxy that reduces the token cost of large upstream tool responses for nearly every other MCP server imaginable. Wraps a single upstream MCP, forwards every call, and handle-ifies fat payloads into content-aware backends the agent can query with a small set of universal verbs (peek, slice, search, aggregate, describe, list_handles).

Benchmarks

Measured end-to-end against two popular real-world MCP servers. Each run fires a fixed script of tool calls twice — once direct, once through jmunch-mcp — with three follow-up jmunch.* verb calls on the proxied side to model an agent drilling into a large result rather than slurping it whole.

suiteupstreamdirect tokensvia jmunch-mcpsaved
GitHub (facebook/react issues/PRs/commits)@modelcontextprotocol/server-github379,87844,328335,550 (88.3%)
Firecrawl (Wikipedia scrapes + site map + search)firecrawl-mcp259,5742,928256,646 (98.9%)

Wall-clock time was also faster with the proxy on both suites, despite the extra verb calls — the agent never has to page through the fat payload:

suitedirectvia jmunch-mcpdelta
GitHub8.4s6.8s−1.6s (−19.0%)
Firecrawl16.4s9.2s−7.2s (−43.9%)

Tabular content (GitHub) routes to the SQLite backend and answers peek/slice/aggregate; JSON content (Firecrawl scrape/map) routes to the JSON-tree backend and answers peek/slice (JSONPath)/search. See bench/README.md to reproduce.

Install

bash
pip install jmunch-mcp

From source:

bash
git clone https://github.com/jgravelle/jmunch-mcpcd jmunch-mcppip install -e .

Quickstart

bash
jmunch-mcp init

init scans three sources — your MCP client configs (Claude Desktop, Claude Code, Cursor, Windsurf, Continue), running processes, and a small catalog of popular upstreams (GitHub, Firecrawl, filesystem, fetch, Brave Search, Slack) — and renders a checklist. Tick the upstreams you want wrapped, and it writes one <name>.toml per selection into ./configs/. Non-interactive flags: --yes (pick everything already registered in a client), --dry-run, --overwrite, --out <dir>, --no-running, --no-catalog.

Manual

bash
jmunch-mcp --config examples/config.toml

Configure your MCP client to launch jmunch-mcp --config <path> instead of the upstream server directly. Add --report to print a session summary on shutdown.

Gateway mode (v2 — universal proxy)

The MCP proxy above saves tokens for MCP clients. The gateway saves tokens for any AI application that speaks the OpenAI or Anthropic HTTP API — LangChain, LlamaIndex, CrewAI, AutoGen, Continue, Cline, Aider, or a raw SDK. No code changes in the app; just point base_url at jmunch.

bash
pip install 'jmunch-mcp[gateway]'jmunch-mcp gateway --config configs/gateway.example.toml# listening on http://127.0.0.1:7879

Point your app:

bash
# OpenAI SDK, LangChain, Aider, Continue, Cline, Ollama-compat apps:export OPENAI_API_BASE=http://127.0.0.1:7879/v1
# Native Anthropic SDK / Claude Code:export ANTHROPIC_BASE_URL=http://127.0.0.1:7879

What it does, transparently:

  • Handle-ifies fat tool_results in outgoing requests — your app's tool returns 100KB of JSON, the model sees a 1KB summary + opaque handle.
  • Injects jmunch verbs (peek, slice, search, aggregate, describe, summarize, list_handles) into the request's tools array so the model can drill in.
  • Short-circuits verb calls — when the model calls jmunch_peek, the gateway resolves it locally against the handle registry and synthesizes the follow-up turn. The app never sees jmunch tool_calls; those completions cost zero upstream tokens.
  • Persists handles to ~/.jmunch/handles.db with a configurable TTL so they survive restarts and cross-session reads.
  • Streams both ways — OpenAI SSE and Anthropic event streams are buffer-then-replayed with correct verb resolution.

Per-request controls via headers:

  • X-Jmunch-Upstream: <name> — override the configured upstream.
  • X-Jmunch-Inject: false — disable tool injection for this call (pure pass-through + request-side handle-ify only).

Metrics flow into the same dashboard as the MCP proxy. Filter with ?surface=gateway or ?surface=mcp on /api/stats and /api/calls.

Dashboard

A read-only local web UI over the metrics DB each proxy writes to. Shows cumulative totals, per-upstream breakdowns, and a time series of forwarded calls.

bash
jmunch-mcp dashboard              # http://127.0.0.1:7878jmunch-mcp dashboard --open       # also open in your default browser

Flags: --port (default 7878), --host (default 127.0.0.1), --db <path> to point at a non-default metrics DB, --open to launch the browser. Metrics only populate once proxies have recorded calls, so run your client against a wrapped upstream first.

License

jmunch-mcp is released under the MIT License — free to use, modify, distribute, and embed in commercial products.

Note that licensing of upstream MCP services you proxy through jmunch-mcp is governed by those services' own terms. This applies to third-party MCP servers (GitHub, filesystem providers, vendor APIs) and to any sibling tools in the broader retrieval ecosystem you may compose with — check each upstream's license before redistribution.

Source: README.md at commit ffa8ca5

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.2.3LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts