MCP Tools

9 tools, one protocol

Everything your AI needs to understand your codebase.

Tool Reference

Detailed documentation for each MCP tool

search_code

Semantic code search by meaning

What It Does

Semantic code search that finds code by meaning rather than exact keyword matches. Instead of searching for "auth_handler", you can ask "where do we handle JWT validation?" and get the relevant files—not just string matches.

Why You'd Use It

Know what you want but not the exact filename or function name? Semantic search understands code semantics, not just text. Perfect for exploring unfamiliar codebases or finding implementation patterns.

Benefits

  • Faster file discovery in large codebases
  • Understands code semantics, not just text matches
  • ~50ms typical query time with indexed codebase

Example Usage

> search_code "where is our auth middleware?"

index_codebase

Index your codebase for semantic search

What It Does

Builds a searchable vector index of your entire codebase. Once indexed, semantic queries return results in ~50ms instead of scanning every file on each search.

Why You'd Use It

This is the one-time setup that enables fast semantic search. Without indexing, every search would scan your entire codebase. With it, searches are instant.

Benefits

  • Enables ~50ms semantic queries
  • One-time setup, ongoing value
  • Local-first: your code stays on your machine

Example Usage

> index_codebase /path/to/project

index_stats

View indexing statistics and health

What It Does

Displays indexing statistics and health metrics: file count, chunk sizes, last update time, index size, and any errors during indexing.

Why You'd Use It

Transparency into the indexing process. Helps diagnose why certain files might not appear in search results or if there are issues with your index.

Benefits

  • See what's been indexed and when
  • Diagnose indexing issues quickly
  • Monitor index health over time

Example Usage

> index_stats

token_stats

Track and optimize token usage

What It Does

Tracks token usage across queries. Shows how many tokens are being used per query, how much context is being injected, and calculates potential savings from context optimization.

Why You'd Use It

Understand the ROI of context optimization. See exactly how many tokens you're saving with semantic search versus naive approaches.

Benefits

  • Quantify cost savings from context optimization
  • Identify queries with high token usage
  • Make informed decisions about context budget

Example Usage

> token_stats --last 10

session_continue

Resume sessions with full context

What It Does

Resumes sessions with full context memory—brings back what was discussed, what files were examined, and what was learned in previous conversation turns.

Why You'd Use It

AI tools typically lose context between sessions. This preserves the knowledge from your work session so you don't have to re-explain your codebase every time.

Benefits

  • Continuity across work sessions
  • No need to re-explain context each session
  • Pick up exactly where you left off

Example Usage

> session_continue --session-id abc123

session_summary

Generate session activity summaries

What It Does

Generates summaries of session activity: what files were read, what was discussed, what was modified, and key decisions made during the session.

Why You'd Use It

Get a quick overview of what happened in a work session. Perfect for onboarding to resume work, or sharing context with teammates.

Benefits

  • Quick session recap
  • Share session context with teammates
  • Faster onboarding to resume work

Example Usage

> session_summary --session-id abc123

register_edit

Track file edits for context coherence

What It Does

Tracks file edits for context coherence. When you edit a file, this tool updates the system's awareness so search results remain accurate.

Why You'd Use It

After making code changes, your index may become stale. Registering edits keeps the context aware of changes without manual re-indexing.

Benefits

  • Keeps search results accurate after changes
  • No manual re-indexing required
  • Automatic context refresh

Example Usage

> register_edit --file src/auth.py

graph_neighbors

Explore code dependencies and connections

What It Does

Explores code dependencies and connections—shows what imports what, what calls what, and the relationships between files and modules in your codebase.

Why You'd Use It

Understand the relationships in your codebase at a glance. When editing a core module, see everything that depends on it before making changes.

Benefits

  • Visualize code relationships
  • Find all dependencies before refactoring
  • Understand module boundaries

Example Usage

> graph_neighbors --file src/core/utils.py

graph_impact

Analyze blast radius of code changes

What It Does

Analyzes the "blast radius" of proposed code changes—shows how many files might be affected downstream if you make a particular change.

Why You'd Use It

Before refactoring, understand the scope of impact. Make informed decisions about whether a change is safe, or what else needs updating.

Benefits

  • Understand change impact before refactoring
  • Make informed refactoring decisions
  • Identify risk surface before large changes

Example Usage

> graph_impact --file src/core/config.py

Ready to get started?

Start using these tools to understand your codebase better.

Read the Docs