MCP.Market

Codeweave MCP server

by semihkayan·io.github.semihkayan/codeweave·v0.1.20·4 stars
No reviews yet

Save tokens while coding — your AI agent gets structured code context, not file dumps.

B82/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B82/100

full report

Adoption
New

4 stars

Reviews

Write one

Nobody has reviewed Codeweave yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Codeweave tools (8)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • get_dependencies

    Show what a function calls — its forward dependencies. IMPORTANT: Use this INSTEAD OF grep or rg to trace what a function calls. Grep gives you text matches that include false positives — this gives you the actual AST-verified call graph. Cross-validates with @deps docstring annotations. Categorizes each dependency as confirmed (AST+docstring), AST-only, docstring-only, or unresolved.

  • get_function_source

    Get the source code of a specific function by name. CRITICAL: Use this INSTEAD OF Read or cat when you need a single function. Reading an entire file to extract one function wastes tokens and pollutes your context window. This returns only the function you need. Supports: plain name ('processOrder'), class.method ('PaymentProcessor.refund'), or partial match. Use context_lines parameter to include

  • get_impact_analysis

    Assess the blast radius of changing a function. IMPORTANT: Use this INSTEAD OF grep or rg to find callers of a function. Grep misses indirect callers, interface implementations, and type relationships — this gives you the complete impact chain with risk levels. Use BEFORE refactoring or modifying function signatures. Combines call graph + type graph. Returns risk levels: high (direct callers + sig

  • get_index_status

    Check index health: how many files/functions are indexed, embedding status, call graph stats, docstring coverage, and language breakdown. CRITICAL: Call this FIRST at the start of a session to verify the index is ready and discover available workspaces. Once confirmed, prefer codeweave tools over generic alternatives: - Exploring a module → get_module_summary (not find/ls/Glob) - Reading one funct

  • get_module_summary

    List all functions and classes in a directory with their signatures. CRITICAL: Use this INSTEAD OF find, ls, tree, or Glob to explore what a module contains. File listings only give you names — this gives you function signatures, summaries, and structure. Saves tokens by showing metadata without source code. Auto-adapts detail level: full for small modules, compact for large ones. Use group_by='su

  • get_stale_docstrings

    Find functions with missing or outdated docstrings. Detects: missing docstrings, @deps that don't match actual AST calls, missing @tags. Use for codebase hygiene. CRITICAL: Run this after writing code. Docstrings with @deps and @tags are what make semantic search, call graph, and impact analysis accurate — without them, the entire tool suite degrades. Fix what this tool reports.

  • reindex

    Manually update the code index. Usually not needed — the server auto-reindexes on file changes. Use after bulk operations or if index seems stale.

  • semantic_search

    Search the codebase by meaning. Works across all workspaces automatically in monorepos. CRITICAL: Use this INSTEAD OF grep or rg when looking for code by concept, feature, or bug area. Unlike text search, this finds functions even when you don't know exact names, spellings, or which files to look in. Use as the FIRST STEP for any code exploration task. Results include workspace, signature, body si

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan107 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 125 days ago8/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 82/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Codeweave compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
82/100
higher than 65% of 4,460 AI and agents servers
Tools
8
the typical AI and agents server has 6
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
4
more than 77% of 2,711 AI and agents servers

What its tools let an agent do: 8 read

Install Codeweave in Claude Code, Cursor or VS Code

Runs npx -y @codeweave/mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add codeweave -- npx -y @codeweave/mcp
Add to Cursor

What the publisher says

From the Codeweave repository's README, as published. We do not edit it. Read it on GitHub

@codeweave/mcp Give your AI agent structured code understanding — not just file dumps.

CodeWeave is an MCP server that gives AI agents cheap, precise code intelligence. Instead of dumping entire files into context, your agent queries local indexes — AST, call graph, type graph, hybrid semantic search — and gets back only what it needs.

Less tokens. More relevant context. Better decisions.

The semantic search pipeline is the heart of the system: a 6-stage hybrid engine combining vector embeddings, full-text search, and structural density scoring. Tested extensively across large production codebases — Java monoliths, TypeScript monorepos, Python ML pipelines, Go microservices — with consistently strong retrieval accuracy.

Actively developed. New tools and improvements ship regularly. Contributions and feedback are welcome.

Quick Start

cd your-project
npx @codeweave/mcp

That's it. The setup wizard handles everything:

  1. Installs @codeweave/mcp globally
  2. Installs Ollama if needed
  3. Downloads the embedding model
  4. Configures your MCP client (Claude Code, VS Code)
  5. Indexes your project

Note: The first run requires a one-time download of Ollama and the embedding model. This takes a few minutes but only happens once.

Open your project in Claude Code or VS Code and start asking questions.

Tools

3 tools organized around the code understanding workflow:

How It Works

Source Code
    │
    ▼
tree-sitter AST  ───>  Function Index (in-memory)
                              │
                   ┌──────────┼──────────┐
                   ▼          ▼          ▼
              Call Graph  Type Graph  Embeddings
              (JSON)      (JSON)     (LanceDB)
                   │          │          │
                   └──────────┼──────────┘
                              ▼
                       3 MCP Tools  ───>  AI Agent
  1. Parse — tree-sitter extracts every function, class, method, and interface across 7 languages
  2. Embed — Qwen3-Embedding-0.6B generates vector embeddings for semantic search
  3. Index — LanceDB stores vectors with BM25 full-text index alongside
  4. Graph — Call graph tracks who-calls-whom with type-aware resolution; type graph tracks inheritance and implementations (powers ranking and index-status reporting)
  5. Watch — File watcher detects changes and incrementally reindexes affected files
  6. Serve — 3 tools exposed over MCP protocol (stdio), ready before indexing completes

Semantic Search

The search pipeline is where CodeWeave really shines. It's not just vector similarity — it's a multi-stage system designed to surface the most relevant and important code:

6-Stage Pipeline:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Codeweave: common questions

Is Codeweave MCP server safe?
Mostly: it is graded B (82/100). Read the Codeweave safety report
How do I install Codeweave?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Codeweave need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Codeweave maintained?
The last commit was 162 days ago (2026-05-26). The latest release is v0.1.20.
What can I use instead of Codeweave?
Servers from other publishers that do the same job: Serena MCP: the IDE for your agent MCP server, Figma Context MCP server and Basic Memory MCP server.
How does Codeweave compare with other AI and agents MCP servers?
safety score 82/100 (higher than 65% of 4,460 AI and agents servers); tools 8 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Codeweave

Same job from other publishers: the closest match first, then the best rated.

  • Serena MCP: the IDE for your agent
    A powerful toolkit for coding, providing semantic retrieval and editing capabilities.
    C
  • Figma Context
    Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
    B
  • Basic Memory
    Local-first knowledge management with bi-directional LLM sync via Markdown files.
    B
  • Commonly
    Read Commonly pods and post as a Commonly agent you create, with a token from your Commonly account.
    A
  • MCP Server for WinDbg Crash Analysis
    A Model Context Protocol server for Windows crash dump analysis using WinDbg/CDB
    A