Jcodemunch Mcp

Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code,…

LLM Mart 4 views 63 listing impressions

jCodeMunch reduces the number of tokens needed for reading code by up to 95% or more. It integrates with multiple AI coding tools and any MCP-compatible client. A pre-built symbol index allows the MCP server to answer code queries in milliseconds with surgical precision.

It serves anyone whose AI agents read code, from solo developers to platform teams managing token budgets across entire organizations. It comes with a guarantee that if it does not pay for itself, the user does not pay. It conforms to an open retrieval standard called jMRI v1.0, which is an Apache-2.0 spec for token-efficient retrieval.

Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.

Related servers

Web search, deep research, prediction markets & crypto data for AI agents. Pay per call via x402.

21 views

Let LLM help you achieve your regression analysis with Stata

21 views

vSphere with Tanzu (VKS): Namespace and TanzuKubernetesCluster lifecycle. Requires vSphere 8.x+.

20 views

Durable agentic memory, encrypted at rest. Fully offline: no network, no API key, no cloud.

19 views