Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

jCodemunch MCP

PYPI · JCODEMUNCH-MCP · SCANNED SEP 20

Token-efficient code exploration via tree-sitter AST parsing. 70+ languages, 86-99% token savings.

Available components

0 this week 84 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 0 of 36 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency35
Schema Quality & AI Usability82
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 993 tokens (~141/item across 7 items; 6 tools + 1 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage97
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 91% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the jCodemunch MCP server?

jCodemunch MCP runs locally as a PyPI package, launched with uvx jcodemunch-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · jcodemunch-mcp

# add to Claude Code
claude mcp add jgravelle-jcodemunch-mcp -- uvx jcodemunch-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "jgravelle-jcodemunch-mcp": {
      "command": "uvx",
      "args": [
        "jcodemunch-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "jgravelle-jcodemunch-mcp": {
      "command": "uvx",
      "args": [
        "jcodemunch-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add jgravelle-jcodemunch-mcp -- uvx jcodemunch-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "jgravelle-jcodemunch-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "jcodemunch-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add jgravelle-jcodemunch-mcp --command uvx --arg jcodemunch-mcp
# ~/.hermes/config.yaml
mcp_servers:
  jgravelle-jcodemunch-mcp:
    command: "uvx"
    args: ["jcodemunch-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "jgravelle-jcodemunch-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "jcodemunch-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add jgravelle-jcodemunch-mcp -t stdio -c uvx -a jcodemunch-mcp
// mcp.json
{
  "mcpServers": {
    "jgravelle-jcodemunch-mcp": {
      "command": "uvx",
      "args": [
        "jcodemunch-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 16 Sept 26 0
    • Stability: pass → unverified security
    • Tool safety: pass → unverified security
    • Capabilities: pass → unverified functional
    • Tool coverage: 100 → unverified functional
    • Schema quality: 100 → unverified functional
    • Package version: 1.108.318 → 1.108.319 functional
  • 15 Sept 26 +15
    • Malware scan: unverified → pass security
  • 14 Sept 26 −15
    • Malware scan: pass → unverified security
  • 11 Sept 26 +1
    • Stability: 0.97 → unverified security
    • Tool safety: pass → unverified security
    • Stability: 0.97 → pass security
    • Capabilities: pass → unverified functional
    • Tool coverage: 100 → unverified functional
    • Schema quality: 100 → unverified functional
    • Package version: 1.108.317 → 1.108.318 functional
  • 10 Sept 26 −1
    • Stability: pass → 0.97 functional
  • 6 Sept 26 +1
    • Stability: 0.97 → pass security
  • 4 Sept 26 +13
    • Stability: fail → 0.93 functional
    • Package version: 1.108.316 → 1.108.317 functional
  • 3 Sept 26 +15
    • Stability: fail → unverified security
    • Tool safety: pass → unverified security
    • Malware scan: unverified → pass security
    • Capabilities: pass → unverified functional
    • Tool coverage: 100 → unverified functional
    • Schema quality: 100 → unverified functional
    • Security disclosure: pass → unverified functional
    • Package version: 1.108.315 → 1.108.316 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed pypi/jcodemunch-mcp@1.108.319

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 36 packages
Packages resolved 36
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 6 exposed · ~786 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
announce_model ~124

Agent self-reports its active model identifier. Server resolves to a tier via model_tier_map (fuzzy: normalize → exact → glob → substring → '*' → 'full') and narrows the exposed tool list accordingly. Idempotent: a second call with the same model is a cheap no-op. Prefer calling plan_turn(model=...) for routine per-task use; use announce_model as a fallback when plan_turn is not appropriate for the current task.

NameTypeReqDescription
modelstringyesYour active model identifier, e.g. 'claude-haiku-4-5'.

No output schema declared.

No examples provided.

jcodemunch_guide ~132

Return the version-current CLAUDE.md / AGENT.md policy snippet for jcodemunch-mcp — the same text produced by `jcodemunch-mcp claude-md --generate`. Lets an agent keep a one-line CLAUDE.md (e.g. "Call jcodemunch_guide and strictly follow its instructions.") instead of pasting a static snippet that drifts from the installed version. Idempotent, no repo context required. Matches the active tool surface, tier and disabled_tools — list 'jcodemunch_guide' in disabled_tools to hide it.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

menu ~86

Discover catalog actions without keeping the full tool catalog resident: menu(query?). Returns compact rows (action, summary, required args, state_changing). With no query, lists the catalog. Pair with 'order' to dispatch the chosen action.

NameTypeReqDescription
limitintegerMax actions to return.
querystringOptional. Keywords describing what you want to do; ranks matching actions.

No output schema declared.

No examples provided.

order ~194

Dispatch any jcodemunch action by name: order(action, args). The single-verb front door to the full tool catalog. Read-only by default — actions that change index/session state require allow_state_change=true, and execution/file-write verbs are refused. For exploration questions ('how does X work'), order('get_ranked_context', {repo, query, token_budget}) answers in ONE call — prefer it over chained search/outline/source hops; add compress=true to fit more symbols in the same budget. Call 'menu' to discover actions, or 'route' to pick one from a task.

NameTypeReqDescription
actionstringyesName of the catalog action to run (e.g. 'search_symbols').
allow_state_changebooleanOpt in to dispatching an index/session state-changing action (e.g. index_repo).
argsobjectArguments for that action, exactly as you'd pass them directly.

No output schema declared.

No examples provided.

route ~155

Map a natural-language task to the best catalog action(s): route(task, repo?, execute?). Returns ranked recommendations with ready-to-run argument templates. With execute=true, dispatches the top recommendation and returns its result in the same call, collapsing discover-then-call into one round-trip. Recommends assemble_task_context / plan_turn for context-gathering intents.

NameTypeReqDescription
executebooleanIf true, dispatch the top recommended action and return its result.
modelstringOptional active model id; piggybacks tier-switch like plan_turn(model=...).
repostringRepository identifier (required to execute repo-scoped actions).
taskstringyesWhat you're trying to do, in plain language.

No output schema declared.

No examples provided.

set_tool_tier ~95

Explicit tier override for the current session. Narrows or widens the exposed tool list to 'core' / 'standard' / 'full'. Prefer plan_turn(model=...) for routine per-task use; use set_tool_tier only for an explicit override (e.g. escalate to 'full' after a capability-gated failure). A narrowing that costs more than it saves is refused.

NameTypeReqDescription
tierstringyes

No output schema declared.

No examples provided.

Common questions

What is the jCodemunch MCP server?

jCodemunch MCP is listed in the public MCP registry as io.github.jgravelle/jcodemunch-mcp. Token-efficient code exploration via tree-sitter AST parsing. 70+ languages, 86-99% token savings. This page covers its PyPI package (jcodemunch-mcp).

Is the jCodemunch MCP server safe to use?

jCodemunch MCP scores 84 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the jCodemunch MCP server expose?

jCodemunch MCP exposes 6 tools: set_tool_tier, announce_model, jcodemunch_guide, order, menu, route. Their descriptions and schemas cost roughly 786 tokens of context every time the server is loaded.

Is the jCodemunch MCP server still maintained?

jCodemunch MCP is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.