Back to Browse

TempoGraph MCP Server

Developer ToolsLow Risk10.0MCP RegistryLocal
Free

Server data from the Official MCP Registry

Code graph context engine with 24 MCP tools. 170+ languages via tree-sitter.

About

Code graph context engine with 24 MCP tools. 170+ languages via tree-sitter.

Security Report

10.0
Low Risk10.0Low Risk

Valid MCP server (2 strong, 1 medium validity signals). No known CVEs in dependencies. Package registry verified. Imported from the Official MCP Registry. Trust signals: 8 highly-trusted packages.

5 files analyzed · 1 issue found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

file_system

Check that this permission is expected for this type of plugin.

How to Install

Add this to your MCP configuration file:

{
  "mcpServers": {
    "tempograph": {
      "command": "uvx",
      "args": [
        "tempograph==0.7.4"
      ]
    }
  }
}

Some servers take additional arguments. See the repository for details.

Documentation

View on GitHub

From the project's GitHub README.

TempoGraph

This is the frozen April-2026 Python line (PyPI tempograph 0.7.4). The live engine is the all-Rust tempograph_rs in Elmoaid/outpm (ruling D-1, 2026-08). The benchmark headline below (+18.6%, p=0.049) was re-analysed as p=0.055, not significant (ruling D-7); it is kept as the published record, not as a current claim. Banner added 2026-09-02.

CI License: AGPL v3 Python 3.11+ TempoGraph MCP server

Your AI agent finds the right files. Every time.

TempoGraph builds a dependency graph of your codebase and gives your AI coding agent exactly the files it needs before making changes. One tool call. No guessing.

The Problem

AI coding agents guess which files to look at. They search by filename, grep for keywords, and hope for the best. In large codebases, they miss critical dependencies, break things downstream, and waste tokens reading irrelevant code.

The Fix

pip install tempograph

Add to your MCP config (Claude Code, Cursor, Windsurf, or any MCP client):

{
  "mcpServers": {
    "tempograph": {
      "command": "tempograph-server",
      "args": []
    }
  }
}

Your agent calls prepare_context with a task description. TempoGraph returns the exact files that matter — based on real dependency analysis, not text matching.

Does It Work?

Tested on real PRs from django, flask, httpx, fastapi, requests, and pydantic. Task: predict which files need to change.

ModelWithout TempoGraphWith TempoGraphImprovement
GPT-4o21.7% F127.5% F1+27%
GPT-4o-mini19.2% F124.5% F1+28%
qwen2.5-coder:32b——+18.6% (p=0.049)

Consistent improvement across every model. 2-3x more tasks helped than hurt. No other code context tool publishes retrieval benchmarks with statistical significance.

How It Works

your repo ──→ tree-sitter parse ──→ symbols + edges ──→ SQLite graph
                                                            │
                    AI agent calls prepare_context ─────────┘
                                                            │
                              ◄── KEY FILES + callers + callees + risk signals
  • Parses your code with tree-sitter into a structural dependency graph
  • Content-hashed and stored in SQLite — only changed files get re-parsed
  • Warm queries in ~21ms. Branch switching doesn't trigger a rebuild
  • Knows when NOT to inject context (adaptive gating avoids harming diffuse commits)

What Else Can It Do?

Beyond prepare_context, TempoGraph exposes 24 MCP tools for deeper analysis when your agent needs it:

ToolWhen to use it
blast_radius"What breaks if I change this file?"
focus"Show me everything related to auth"
hotspots"Which files are riskiest to change?"
dead_code"What can I safely delete?"
diff_context"What's the impact of my current changes?"
overview"Orient me in this new codebase"
ToolWhat it does
prepare_contextOne-shot context for a task — the primary tool
overviewRepository orientation: size, languages, entry points
focusConnected subgraph around a symbol — callers, callees
blast_radiusWhat breaks if you change this file or symbol
diff_contextImpact analysis of changed files
hotspotsRanked risk list — complexity x coupling x size
dead_codeUnreferenced symbols — cleanup candidates
lookup"Where is X?", "What calls X?"
dependenciesCircular imports, dependency layers
architectureModule-level dependency view
symbolsFull symbol inventory
file_mapFile tree with top symbols per file
search_semanticHybrid keyword + vector + structural search
cochange_contextFiles that historically change together
suggest_nextPredicts the next useful tool call
run_kitComposable multi-tool workflows
statsToken budget estimates
get_patternsCodebase conventions and idioms
report_feedbackLog whether output was useful
learn_recommendationSuggestions from feedback history
index_repoBuild or rebuild the graph
watch_repo / unwatch_repoLive incremental updates
embed_repoGenerate vector embeddings

CLI

# Orient in a new repo
tempograph ./my-project --mode overview

# What's connected to auth?
tempograph ./my-project --mode focus --query "authentication"

# What breaks if I touch db.ts?
tempograph ./my-project --mode blast --file src/lib/db.ts

# Find dead code to clean up
tempograph ./my-project --mode dead

Python API

from tempograph import build_graph

graph = build_graph("./my-project")
results = graph.search_symbols("handleLogin")
importers = graph.importers_of("src/lib/db.ts")
dead = graph.find_dead_code()

Languages

Python, TypeScript, JavaScript, Rust, Go, Java, C#, and Ruby get deep extraction (custom tree-sitter handlers). 170+ additional languages are supported via generic handler. pip install tempograph[full] for everything.

Support & Sponsorship

If TempoGraph saves you time, consider sponsoring the project. Sponsors get early access to new features.

Sponsor

Commercial Licensing

TempoGraph is AGPL-3.0 — free to use, modify, and distribute. If you use TempoGraph in a network service (SaaS, hosted IDE, AI coding platform), AGPL requires you to open-source your service code. If that doesn't work for you, commercial licenses are available.

Contact eali@needspec.com for commercial licensing terms.

License

AGPL-3.0 — free to use. Network service use requires source disclosure, or a commercial license.

Reviews

No reviews yet

Be the first to review this server!