codeindex

<img src="docs/brand/logo.svg" alt="codeindex" width="235" height="70">

A structural code intelligence engine that runs as an MCP server for AI coding agents.

It indexes your codebase with tree-sitter (40+ languages), builds a trigram full-text index, an inverted word index, and a dependency graph — then exposes them through 16 MCP tools.

 ┌─────────────┐   MCP (stdio)   ┌───────────┐            ┌──────────────────┐
 │  AI Agent   │ ◄─────────────► │ codeindex │  socket    │ codeindex daemon │
 │ (Claude,    │ 16 tools,       │  (relay)  │ ◄────────► │  one per         │
 │  Cursor…)   │ JSON-RPC        └───────────┘            │  workspace       │
 └─────────────┘                                          └────────┬─────────┘
 ┌─────────────┐   MCP (stdio)   ┌───────────┐                     │
 │  AI Agent   │ ◄─────────────► │ codeindex │ ◄───────────────────┘
 │  (session 2)│                 │  (relay)  │   tree-sitter parse (40+ langs)
 └─────────────┘                 └───────────┘   trigram + word index
                                                 dependency graph
                                                 one file watcher
                                                 snapshot persistence

Every session on a repository speaks plain stdio MCP, as before. Behind that, they share one index: the tree is parsed once, watched once and written once, however many agents are attached. Eight sessions on one repository used to be eight copies of the same index, eight file watchers and eight writers of the same snapshot; measured on a 720-file project, each session went from 87 MB to 7 MB, against one shared 77 MB daemon.

Why

AI coding agents spend tokens reading entire files. codeindex answers structural questions — symbol outlines, definitions, callers, blast radius, dependency chains — in a few hundred tokens instead of thousands.

One plan_change call returns: where a symbol is defined, every call site, the file's architectural role (god module / stable core / island / driver), hardcoded literals to check, and the full transitive blast radius if the file changes.

Quickstart

The shortest path, if you have Node 18+. Nothing else to install, no key, no config — the package is a 4 KB wrapper that fetches the binary for your platform and verifies it against the published checksums:

claude mcp add codeindex -- npx -y @munhq/codeindex

No Node, or you want the skill and the hook as well:

# Prebuilt binary + skill + MCP registration, in one command
curl -fsSL https://raw.githubusercontent.com/munhq/codeindex/main/install.sh | sh

# Or build from source:
cd zig && ./fetch-vendor.sh && zig build -Doptimize=ReleaseFast

Docker, for hosts that install MCP servers as images. The workspace is bind-mounted read-only; codeindex never writes to it:

docker run -i --rm -v "$PWD:/workspace:ro" munhq/codeindex

Register with your AI agent:

# Claude Code — the plugin is the one-step path. It ships the skill, both
# routing hooks and the MCP server together, and its launcher finds or fetches
# the binary.
claude plugin marketplace add munhq/codeindex
claude plugin install codeindex@codeindex

# Without the plugin (or for a different MCP client), register the binary
# directly. Do not do both: two registrations mean two servers, two copies of
# every tool schema, and two writers on one snapshot. install.sh detects the
# plugin and skips this step when it is present.
claude mcp add -s user codeindex -- ~/.local/bin/codeindex --mcp

# Cursor / Claude Desktop / other MCP clients: add to your config
{
  "mcpServers": {
    "codeindex": {
      "command": "npx",
      "args": ["-y", "@munhq/codeindex"]
    }
  }
}

Every listing points at the same server: npm @munhq/codeindex, the official MCP registry as io.github.munhq/codeindex, and Smithery as munhq/codeindex.

The next time your agent starts, codeindex indexes your project in the background and serves structural queries.

MCP Tools

| Tool | What it does | |------|-------------| | status | Index stats: file count, symbol count, indexing state, token savings %, the indexed workspace and whether a watcher is live | | search | Trigram-accelerated full-text search across all indexed files | | find_symbol | Find symbol definitions (functions, structs, classes…) by name | | find_word | Exact word/identifier lookup in the inverted word index | | find_callers | Approximate callers of a symbol (heuristic, no full name resolution) | | get_outline | Structural outline of a file (symbols, line counts) | | get_tree | Directory tree with file metadata | | get_imports | What files does a given file import/depend on | | get_imported_by | Reverse dependencies — who imports this file | | get_change_impact | Transitive blast radius: what breaks if a file changes | | plan_change | Full refactor plan for a symbol or file — definitions, callers, file role, literals, blast radius | | get_hot_files | Recently changed files sorted by recency | | read_file | Read file contents with optional line range | | read_symbol | Read just a symbol's source code (with optional context lines) | | index_workspace | Index or re-index a workspace directory | | analyze | Run one of 21 code analyses (see below) |

Analyses (analyze tool)

| Analysis | What it finds | |----------|--------------| | security | Hardcoded secrets, SQL injection patterns, unsafe blocks, eval usage | | dead_code | Unreferenced files and symbols | | unwrap_audit | .unwrap() / panic-prone error handling (Rust) | | test_coverage | Files without test coverage | | architecture | Architectural smells — god modules, circular deps, islands | | crossref | Cross-file symbol references | | type_drift | Type signature mismatches across modules | | db_schema | Database schema drift between migrations and code | | migration_parity | Missing migrations for schema changes | | manifest_compliance | package.json / Cargo.toml / go.mod compliance issues | | literal_scan | Hardcoded URLs, IPs, ports, absolute paths, TODOs | | coupling | Module coupling metrics | | cycles | Circular dependency detection | | duplication | Reinvented free functions — the same job written twice | | clones | Copy-pasted function bodies, ignoring names and whitespace | | spawn_scan | An interpreter started on a loop or a timer, ranked by startup cost times spawn rate | | deps | Dependency inventory — duplicate versions, unreferenced crates, single-use crates | | leak_shapes | Shapes a leak has, each paired with the runtime series that decides it | | logic_shapes | A fixed byte constant against a declared memory limit, and a round trip per row | | field_contention | One declared-state field written by two or more owners | | health | Roll-up of the analyses above into one index-health report |

Supported Languages

40+ languages via tree-sitter: Rust, Python, TypeScript/TSX, Go, Zig, C, C++, Java, Ruby, Bash, C#, Kotlin, Lua, Scala, Elixir, R, Swift, Dart, Haskell, TOML, JSON, YAML, HTML, CSS, SCSS, SQL, HCL, Dockerfile, Markdown, Nix, Make, and more.

Configuration

codeindex --mcp                          # Run as MCP server (stdio)
codeindex --mcp --no-daemon              # ...without sharing the workspace daemon
codeindex --daemon-idle-secs 0           # Keep the daemon resident indefinitely
codeindex --workspace ./my-project       # Index a specific directory
codeindex --project-id my-project        # Project identifier
codeindex -v                             # Print version
codeindex -h                             # Print help

# Environment variables
CODEINDEX_WORKSPACE=/path/to/project     # Same as --workspace
CODEINDEX_PROJECT_ID=my-project          # Same as --project-id

Getting it used

A server that registers without telling an agent when to reach for it stays idle, and an idle index saves nothing however cheap its calls are. The plugin ships three things for that, in the order they act:

1. A SessionStart brief. About 240 tokens, once per session, in a repository that holds source files: codeindex is live, and here is the tool for each kind of code question. It lands before the agent has chosen a tool, which is the only moment that can change the first choice.
2. A PreToolUse hint. Fires on the 1st, 8th and 25th code question of a session, when a scan is about to answer something the index answers better, and names the tool for that exact question. It matches Bash as well as Read/Grep/Glob, because a permission mode that routes file work through the shell is where most scans actually happen.
3. The skill, which the model loads when it decides the task calls for it.

Advice loses to habit, so the narrow case where the index is strictly better is refused rather than argued with: an identifier search that is the whole command line, in a project that has been indexed before. It never refuses a file read — the bytes are required before an Edit — never refuses a line that also builds or tests, and stops refusing after three times in a session, so it can never be the reason a session cannot proceed.

That is on by default, and it is one switch to turn off — no file to edit by hand. It is a plugin option, so /plugin shows it as "Refuse a scan the index answers better" and Claude Code passes your answer to the hook. Outside the plugin, or for a single session, CODEINDEX_ENFORCE=0 in the environment overrides the option and CODEINDEX_ENFORCE=1 restores it.

Measure the effect rather than assuming it: python3 plugin/measure_routing.py counts, per session, how many code questions went to a scan and how many went to the index, across every Claude Code home on the machine.

Which tree gets indexed

In --mcp mode the working directory belongs to the client, not to you, and it is regularly not your project: Claude Code launches a plugin's MCP server from the plugin's own directory and a user-scope server from its config directory. So the workspace is resolved in this order, and the first usable answer wins:

1. --workspace or CODEINDEX_WORKSPACE. An explicit answer is never overridden.
2. CLAUDE_PROJECT_DIR, which Claude Code sets in every MCP server it spawns.
3. The launch directory, walking up for a .git, package.json, Cargo.toml, go.mod, build.zig or pyproject.toml marker.
4. The client's MCP roots. The server asks for them at the handshake whenever the root above was a guess, and adopts one when the guess was refused or lands outside every root the client reports. notifications/roots/list_changed is honoured too, so a directory added with --add-dir can still rescue a session.

status reports the effective root as workspace, and whether a file watcher is running as watcher. Check them wh