Codemesh
Intelligent code knowledge graph for AI coding agents — 71% cheaper, 72% faster
Connector by pyalwin · GitHub account verified by the MCP Registry
Chalk Labs
Need help deploying Codemesh?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.
npx agentmarket install connector/pyalwin-codemesh
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.
- Tools
- 6 read · 4 write · 0 delete · 1 not yet classified
- Secrets
- None asked for
- Install scripts
- Not scanned yet
- Runs as
- Node.js package
Tools by what they do 11
Read from the source code; the running server may list different tools.
Read 6 · Look things up without changing anything.
codemesh_answercodemesh_explorecodemesh_inspectcodemesh_recallcodemesh_sourcecodemesh_status
Write 4 · Create, change, send or run things.
codemesh_enrichcodemesh_hydratecodemesh_mapcodemesh_workflow
Not yet classified 1 · We could not tell from the name and description.
codemesh_trace
Secrets and settings it asks for
Other settings (environment variables or headers).
CODEMESH_PROJECT_ROOT
Files it touches
- Any path the agent passes to its tools
Tools (11)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
codemesh_answerOptional one-call context assembly for a code question. Returns ranked files, inline source snippets, suggested reads, concepts, workflows, and call graph. For deterministic, model-directed navigation, start with codemesh_map instead.
codemesh_enrichAdd an AI-generated concept (summary/insight) linked to a file or symbol. Creates a ConceptNode with a describes edge.
codemesh_exploreOmni-tool for exploring the codebase. Use 'search' to find things by text, 'context' to see relations of a specific file/symbol, and 'impact' to find reverse dependencies (trace).
codemesh_hydrateReopen up to eight saved symbol references after a handoff or compaction. Verifies saved hashes against current source and returns exact full source within byte and symbol budgets. Every reference has an explicit outcome, including fresh, changed, stale, missing, ambiguous, omitted, or error.
codemesh_inspectInspect a symbol and verified direct callees, callers, or both. Indexed links are candidate hints; incoming discovery can be incomplete. Returns whole exact source blocks within byte/symbol budgets, with omitted and unresolved relationships explicit.
codemesh_mapNavigate the indexed codebase one level at a time. Call with no arguments for the repository root; pass an entry's node ID to expand it; use relation to follow one-hop graph links. Results are bounded and paginated, with stable IDs and no source code. Use codemesh_source for an exact symbol when needed. Legacy query/symbol call-tree search remains available.
codemesh_recallRetrieve prior agent notes and workflows by exact path/symbol or text. Each result reports whether its source revision is still current.
codemesh_sourceRead a revision-checked symbol, preferably by exact ID. Unique symbol names also resolve; ambiguous names return candidate IDs and spans. Use auto for bounded navigation, full for edits, and ifHash only when matching bytes remain in context. If stale, re-index before relying on line ranges.
codemesh_statusGet statistics about the knowledge graph: node counts by type, edge counts by type, stale count, and last indexed timestamp.
codemesh_traceTrace a call chain from a symbol to its leaf nodes. Follows calls/callers edges through the graph and returns every function in the path. Use this AFTER codemesh_explore to follow a specific execution flow to completion.
codemesh_workflowCreate a workflow that links files in a logical sequence (e.g. request flow, data pipeline). Creates a WorkflowNode with traverses edges.
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit
- Oct 20, 2026 (11 days ago)
- Last release
- Apr 20, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- Registry name
io.github.pyalwin/codemesh- Version
- 0.1.2
- Auth
- No auth
- Packages
- npm @pyalwin/codemesh
- License
- MIT
- Repository
- github.com/pyalwin/codemesh
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get Codemesh running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
Codemesh MCP server. Agent Mart. https://agentmart.dev/connectors/pyalwin-codemesh (last updated 2026-10-24)