Agentmap MCP server
The TS/JS-accurate repo map for coding agents: ts-morph import/symbol/call graph + MCP query tools
48 stars156 downloads/wk
Reviews
Write oneNobody has reviewed Agentmap yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Agentmap tools (14)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
affectedWhich test files cover a source file, following import edges transitively — and, just as usefully, whether ANY do. Answers 'what do I re-run after changing this' before the edit, not after CI. Walks runtime AND type-only edges, so a file imported only via `import type` still reports its covering tests. An empty list is the ANSWER (nothing covers this file), not a lookup failure.
anyUnified router: resolve a query against the repo map (file → symbol → feature) then fall back to a live git-grep for string/copy/data literals. Best default for 'where is X' / reuse-before-rebuild.
callersCompiler-accurate call graph: every call site that INVOKES a symbol, resolved by the TypeScript language service (not tree-sitter name-matching) — so a type-position mention, a re-export, or a same-named local in another file is never mis-attributed. Symbol-level blast radius: 'who breaks if I change this function'. A deliberate DEEP query — the first call warms the TS type-checker (seconds on a l
callsCompiler-accurate OUTGOING call graph: every in-project symbol that a given symbol INVOKES, resolved by the TypeScript language service (not tree-sitter name-matching) — callee resolution follows real bindings (imports/re-exports) through to the actual declaration. Answers 'what does this function call / depend on'. node_modules and TS built-ins are excluded; dynamic dispatch and higher-order indi
featureList all files belonging to a named feature plus its external dependents.
featuresList every detected feature (top-level app/ route segment) with its file count.
findFind every symbol whose name matches (substring, case-insensitive) — exported symbols plus non-exported top-level declarations. Use to locate a function/class/type before rebuilding it. A match reached through a re-export barrel carries `definedIn` — the file that actually declares it, resolved by the TypeScript checker through any number of barrel hops — or `external: true` when the origin is out
hubsList the most important files in the repo by PageRank (the hubs everything imports). Read these first to understand a codebase.
mapToken-budgeted ranked digest of the codebase (PageRank + Aider-style symbol ranking). Optionally focus toward a file and/or set a token budget.
relatesBlast radius for a file: its exports, imports, direct dependents, and the files most related to it by random-walk relevance. Use before editing to see who breaks. `dependents` means 'breaks at RUNTIME'; files that depend on this one only through `import type` are listed separately as `typeOnlyDependents` — they break at COMPILE time when an export is renamed or removed, so check both before a rena
routeResolve one URL path (e.g. '/dashboard/settings') to the files that serve it, including the layouts it nests under. Use to go from a bug report naming a URL straight to the code. Next.js App Router only.
routesThe Next.js App Router route table: every URL path the repo serves, with the file that serves it. Next.js only — on any other repo this returns an explicit `reason` rather than an empty list.
searchRank symbols by BM25 lexical relevance for a VAGUE natural-language query (e.g. 'where's the auth retry logic', 'the function that dedupes symbols') — where exact `find`/`any` name matching fails. Tokenizes symbol names + path segments + feature + kind, scored by BM25 and fused with file PageRank. Best when you don't know the exact symbol name.
symbolsTop N globally ranked symbols (Aider-style importance). Defaults to 30.
Public scan report
scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it
- Code scan13 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 5 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
What the publisher says
From the Agentmap repository's README, as published. We do not edit it. Read it on GitHub
= 20">
agentmap
Your agent burns most of its context just finding code. This gives it the answer in one line.
npx @raymondchins/agentmap --relates lib/db/schema.tsrelates: lib/db/schema.ts (pr 0.073744)
dependents (21): lib/types.ts, lib/utils.ts, lib/db/queries.ts,
components/chat/message.tsx, app/(chat)/api/chat/route.ts, …Every file on that list really imports it. grep gets 40% of them wrong.
💸 What it saves
Token cost of the hidden first step in every agent task — find the relevant code — on a real 154-file Next.js app (vercel/ai-chatbot, sha 2becdb4):
Holds on zod too (367 files, 99.2%) and taxonomy (125 files, 96.0%). Captured output, pinned shas → benchmark/RESULTS.md
🎯 …and it's still right
Fewer tokens is worthless if they're the wrong ones. Separate eval, ground truth derived live from real repos:
n=42 dependents / n=75 definitions across zod, zustand, hono. Re-run: npm run eval · method → EVAL.md
⚡ The five commands
--any routes it for you: file → symbol → feature → live content search.
Cold build ~1.2s. Cached query ~0.1s. No server, no vector DB, no API key.
🔌 Setup
npx @raymondchins/agentmap --install-hooks # rebuild on commit + steer the agent to the map
npx @raymondchins/agentmap --install-skill # Claude Code · Cursor · Codex · Gemini · OpenCode · CopilotShortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Install directly
Runs npx -y @raymondchins/agentmap on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add agentmap -- npx -y @raymondchins/agentmap
Agentmap: common questions
- Is Agentmap MCP server safe?
- Yes, by our scan: it is graded A (92/100). Read the Agentmap safety report
- How do I install Agentmap?
- It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
- Does Agentmap need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Agentmap maintained?
- The last commit was 5 days ago (2026-09-19). The latest release is v0.22.0.
- What can I use instead of Agentmap?
- Servers from other publishers that do the same job: Repo Graph MCP server, Dekko MCP server and Wayfinder MCP server. Compare all Agentmap alternatives.
Alternatives to Agentmap
Same job from other publishers: the closest match first, then the best rated.
- Repo GraphStructural graph map of any codebase so LLMs navigate by structure, not guesswork.not reviewedGrowingA
- DekkoStatic code map generator: MAP.md + map.json for any repo, plus a Claude Code /map pluginnot reviewedGrowingA
- WayfinderRead local AI coding paths, decisions, and branches as an in-host voyage map.not reviewedGrowingB
- Codna — repository intelligenceMap a repo before spending a token: triage, bug-fix PRs, SARIF reachability, on-device recall.not reviewedNewB
- FlowzapCreate workflow, sequence, architecture, and mind map diagrams via AI assistants.not reviewedGrowingA