Sense MCP Server

Codebase understanding for AI coding agents — symbol graph, blast radius, semantic search. That is what the sense mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

Your AI agent reads 19 files to answer "who calls this function?" because it has the text of your codebase but never the map. It re-derives structure on every task, burns tokens chasing grep chains, and hallucinates dependencies that don't exist. Sense indexes your repo once and serves a symbol graph plus semantic code search over MCP. Claude Code, Cursor, Codex CLI, and any MCP client finish the same task in 10 tool calls instead of 19, on 156K tokens instead of 228K, with the same correctness (bench/).

The tools it exposes

The server publishes 14 tools. What each one is for:

• sense_graph — Symbol relationships, callers, callees, inheritance, tests, dead code
• sense_search — Hybrid bi-encoder + cross-encoder semantic code search with keyword and text fallback
• sense_blast — Blast radius, affected code, affected tests, risk score
• sense_conventions — Detected project conventions from source
• Metric — Claude Code (Opus 4.6)
• Operation — Measured (p50 / p95)
• Conventions — 16ms / 16ms
• Platform — Status
• Windows — Supported using WSL2
• Language — Framework support
• Ruby — Rails (associations, callbacks, routes), Stimulus, Turbo
• ERB — Stimulus, Turbo (cross-language edges to JS controllers)

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

What it needs from you

• ~60 MB disk for the binary - 100-200 MB for the .sense/ index (varies with project size)

How it compares

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Sense's toolset — sense_graph, sense_search, sense_blast and 11 more — is a fair guide to whether it matches your workflow. It is maintained by luuuc; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Sense's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Sense.
• Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.