# jCodeMunch MCP: Stop Paying AI to Read Whole Files (95%+ Token Cut)

> jCodeMunch is a model-agnostic MCP server that indexes a codebase with tree-sitter AST parsing and delivers exact function, class, and constant retrieval to AI coding agents (Claude, GPT, Gemini, and any MCP-compatible client) instead of full-file reads. Measured 95%+ average token reduction across 15 tasks on 3 real repositories, with cumulative production telemetry showing over 1 trillion input tokens prevented across more than 200,000 participating installations.

## Callable Tools (WebMCP)

Pages on jcodemunch.com register WebMCP tools via the browser's `document.modelContext`
(W3C Web Machine Learning CG). An agent in a supporting browser can call these instead of
parsing the rendered HTML.

- `jcm_site_guide`, what this page is and which tools it exposes (every page)
- `jcm_list_alternatives`, every direct alternative and complementary tool on the comparison page (versus.php)
- `jcm_compare`, full side-by-side against one named alternative (versus.php)
- `jcm_search_comparison`, search every matrix cell, e.g. "which alternatives are AGPL" (versus.php)
- `jcm_estimate_roi`, license payback period at a given query volume (roi.php)
- `jcm_estimate_mcp_schema_tax`, per-turn tool-schema overhead for a set of MCP servers (token-tax-calculator.php)

Without a WebMCP-capable browser, every page still answers to `Accept: text/markdown`.

## Core Content

[Model-agnostic MCP Server](https://github.com/jgravelle/jcodemunch-mcp)
- Indexes any repository (tree-sitter AST parsing) for symbol-level retrieval
- Supports any MCP-compatible client: Claude Code, Cursor, Antigravity, Gemini, Windsurf, Codex
- Replaces full-file reads with exact function/class/method byte-offset retrieval in O(1) time
- Local-first by default; no cloud lock-in, no code leaving the developer's machine
- Source available on GitHub; free for non-commercial use, commercial licenses available for organizational use

[Landing Page](https://jcodemunch.com/index.php)
- Live token-savings counter sourced from anonymous production telemetry (on by default, one setting switches it off)
- Live CO2 savings counter (Green Software Practitioner methodology)
- Side-by-side benchmark comparisons against the "read all files" baseline
- Pricing tiers and one-command install path

[Benchmarks](https://github.com/jgravelle/jcodemunch-mcp/blob/main/benchmarks/README.md)
- 96.2% average token reduction (26.5x) vs a grep-and-read agent, tiktoken cl100k_base, 15 tasks
- Per-repo figures: expressjs/express, fastapi/fastapi, gin-gonic/gin
- Per-query range 7.6x to 77.2x (median 19.1x); against read-all the figure is 99.6%, a ceiling nobody pays
- Harness, queries, and per-iteration data fully reproducible from the repository

## Resources

[Token Reduction as an Energy-Efficiency Action (Wiki)](https://github.com/jgravelle/jcodemunch-mcp/wiki/Token-Reduction-as-an-Energy-Efficiency-Action)
- Case study applying ISO/IEC 21031:2024 (Software Carbon Intensity) to LLM tooling
- Methodology, boundary definition, functional-unit choice, baseline comparison
- Invariant-ratio argument: per-task SCI reduction holds regardless of which per-token energy estimate one accepts
- Author credentials: Green Software Foundation Practitioner

[ROI Calculator](https://jcodemunch.com/roi.php)
- Estimate payback period based on team size and query volume
- Calculate dollar savings against Claude/GPT/Gemini API rates
- Compare against subsidized-plan limit-extension benefits

[Token Tax Calculator](https://jcodemunch.com/token-tax-calculator.php)
- Models the ongoing cost of feeding entire files to LLMs versus targeted symbol retrieval
- Sensitivity analysis across model choice and query patterns

[Competitive Comparison](https://jcodemunch.com/versus.php)
- Side-by-side feature comparisons against other code-retrieval tooling
- AST-accurate retrieval vs. chunk-based RAG: the geometric argument
- Local-first vs. cloud-bound architectures
- One page per comparison for the tools people ask about most: [Serena](https://jcodemunch.com/vs/serena.php), [caveman](https://jcodemunch.com/vs/caveman.php), [Ponytail](https://jcodemunch.com/vs/ponytail.php), [RTK](https://jcodemunch.com/vs/rtk.php), [Headroom](https://jcodemunch.com/vs/headroom.php), [CodeGraph](https://jcodemunch.com/vs/codegraph.php), [GitNexus](https://jcodemunch.com/vs/gitnexus.php), [Repomix](https://jcodemunch.com/vs/repomix.php), [Context Mode](https://jcodemunch.com/vs/context-mode.php), [RepoMapper](https://jcodemunch.com/vs/repomapper.php), [codebase-memory-mcp](https://jcodemunch.com/vs/codebase-memory-mcp.php)
- [caveman vs Ponytail vs RTK vs Headroom vs jCodeMunch](https://jcodemunch.com/vs/caveman-vs-rtk-vs-headroom.php): which one saves which kind of token

## Audience Pages

[For Developers](https://jcodemunch.com/for-developers.php)
- Hands-on integration with Claude Code, Cursor, Antigravity, and other MCP clients
- Hook configuration for auto-reindex on file save
- Common workflow patterns

[For Engineering Leads](https://jcodemunch.com/for-leads.php)
- Organizational token-budget management
- Adoption rollout patterns
- Studio and Platform licensing tiers

[For Finance](https://jcodemunch.com/for-finance.php)
- Scope-3 emissions impact of LLM tooling spend
- Per-developer cost projections
- Procurement-ready documentation

## Optional

[Recognition & Testimonials](https://jcodemunch.com/recognition.php)
- Mentions from industry practitioners and writers
- User-reported savings stories
- Wall of Love

[Teams](https://jcodemunch.com/teams.php)
- org-rollup totals every seat's savings; try it for 14 days with no key
- States exactly what the evaluation and the license check send

[Guarantee](https://jcodemunch.com/guarantee.php)
- 30 days to try it with the anonymous savings telemetry on; refund on request
- Says who it is for and how to get your money back

[Tool Surface](https://jcodemunch.com/descriptions.php)
- Full descriptions of jCodeMunch's MCP tools
- Tool-tier profiles (core, standard, full) for fitting under MCP client tool-count caps

[Sibling MCPs](https://github.com/jgravelle)
- jDocMunch: documentation section indexing
- jDataMunch: tabular data (CSV/Excel) retrieval
- All three follow the same local-first, symbol-anchored retrieval philosophy

**Note:** Canonical documentation, install instructions, and technical guides live in the [GitHub repository](https://github.com/jgravelle/jcodemunch-mcp). The landing page and resources above are derived from that source of truth.