MCP.Market

Contextweaver MCP server

by wchiway·io.github.wchiway/contextweaver·v1.5.4·2 stars

Semantic code retrieval engine with hybrid search, context expansion, and 40+ language support.

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

full report

Adoption
New

2 stars51 downloads/wk

Reviews

Write one

Nobody has reviewed Contextweaver yet.

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

Contextweaver tools (6)

write = sends, deletes, buys or posts

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

  • codebase-retrieval

    IMPORTANT: This is the PRIMARY tool for searching the codebase. It uses a hybrid engine (Semantic + Exact Match) to find relevant code. Think of it as the "Google Search" for this repository. Capabilities: 1. Semantic Search: Understands "what code does" (e.g., "auth logic") via high-dimensional embeddings. 2. Exact Match: Filters by precise symbols (e.g., class names) via FTS (Full Text Search).

  • find-references

    Find heuristic text references to a known symbol across indexed chunks. Use this when: - you know the exact symbol name - you want likely usage sites Limits: - heuristic text search, not compiler-accurate references - for exhaustive raw text matching, use grep outside MCP

  • get-symbol-definition

    Find likely symbol definitions for a known symbol name. Use this when: - you know the exact symbol name - you want the defining code block Limits: - heuristic definition lookup, not compiler-accurate navigation - ranks breadcrumb matches first, then definition-pattern FTS fallback

  • list-files

    List indexed files for quick structural exploration. Use this when you want: - repository structure - file paths, languages, and sizes - zero embedding API cost This is a metadata view, not semantic retrieval.

  • list-symbols

    List all symbols (functions, classes, interfaces, etc.) in the codebase with optional filtering. Use this when: - You want an overview of available symbols in a directory/file - You need to browse the symbol structure of the codebase - You want to filter symbols by type, language, or path Returns: - Grouped by file, ordered by line number - Symbol kind (function, class, interface, etc.) - Line ran

  • stats

    Show ContextWeaver index/search/health statistics for a repository. Returns three sections: 1. Index process: last index run snapshot + cumulative run count. 2. Search quality/behavior: cumulative queries, cache hit rate, average per-stage latency (retrieve/rerank/expand/pack), average recall. 3. Health/consistency: file count, language breakdown, LanceDB vector row count, embedding dimensions, mi

Public scan report

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

no findings
  • Code scan35 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 106 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 Contextweaver compares

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

Safety score
82/100
higher than 68% of 3,470 Web search servers
Tools
6
the typical Web search server has 5
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
2
more than 70% of 1,786 Web search servers
Downloads a week
51
more than 36% of 827 Web search servers with a package

What its tools let an agent do: 6 read

Install Contextweaver in Claude Code, Cursor or VS Code

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

claude mcp add contextweaver -- npx -y @chiway/contextweaver
Add to Cursor

What the publisher says

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

ContextWeaver

🧵 A codebase context engine woven for AI agents

Semantic Code Retrieval for AI Agents — Hybrid Search • Graph Expansion • Token-Aware Packing

English · 简体中文

ContextWeaver is a semantic retrieval engine purpose-built for AI coding assistants. It combines hybrid search (vector + lexical), intelligent context expansion, and token-aware packing to deliver precise, relevant, and context-complete code snippets to LLMs.

✨ Core Features

🔍 Hybrid Retrieval Engine

  • Vector Retrieval: deep semantic understanding via similarity
  • Lexical Retrieval (FTS): exact matching for function names, class names, and other technical terms
  • RRF Fusion (Reciprocal Rank Fusion): intelligently merges multiple recall channels

🧠 AST Semantic Chunking

  • Tree-sitter parsing: supports TypeScript, JavaScript, Python, Go, Java, Rust, C, C++, C#, and more
  • Dual-Text strategy: displayCode for presentation, vectorText for embedding
  • Gap-Aware merging: handles code gaps intelligently while preserving semantic integrity
  • Breadcrumb injection: vector text carries hierarchical paths to boost recall
  • UTF-16 character-domain normalization: offsets are unified via SourceAdapter.toCharOffset before writing metadata, preventing multi-byte character slicing errors (v1.4.0+)

📊 Three-Stage Context Expansion

  • E1 Neighbor expansion: adjacent chunks within the same file, preserving block completeness
  • E2 Breadcrumb completion: sibling methods under the same class/function for structural understanding
  • E3 Import resolution: cross-file dependency tracking (configurable toggle)

🎯 Smart TopK Cutoff

  • Anchor & Floor: dynamic threshold plus an absolute floor as dual safeguards
  • Delta Guard: prevents misjudgment in Top1-outlier scenarios
  • Safe Harbor: the first N results only check the floor, guaranteeing baseline recall

🔌 Native MCP Support

  • MCP Server mode: launch a Model Context Protocol server with one command
  • Multi-tool granularity (v1.5.0+): beyond core semantic retrieval, adds dedicated tools for structure browsing, symbol references, symbol definitions, and statistics
  • Intent/term separation: an LLM-friendly API design
  • Auto-indexing: the first query triggers indexing automatically; incremental updates are transparent

Shortened. The full README is on GitHub.

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

Contextweaver: common questions

Is Contextweaver MCP server safe?
Mostly: it is graded B (82/100). Read the Contextweaver safety report
How do I install Contextweaver?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Contextweaver need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Contextweaver maintained?
The last commit was 144 days ago (2026-06-13). The latest release is v1.5.4.
What can I use instead of Contextweaver?
Servers from other publishers that do the same job: Vexor MCP server, M3 Memory MCP server and Arxiv MCP server.
How does Contextweaver compare with other Web search MCP servers?
safety score 82/100 (higher than 68% of 3,470 Web search servers); tools 6 (the typical Web search server has 5); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Contextweaver

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

  • Vexor
    A semantic search engine for files and code.
    B
  • M3 Memory
    Local-first, cloud-friendly memory — 100+ tools, 99.2% LongMemEval-S retrieval@8, hybrid search.
    A
  • Arxiv
    Search arXiv papers, download full text, semantic search, citation graphs, and alerts via MCP.
    A
  • Socraticode
    MCP server for enterprise local codebase indexing, semantic search, and code dependency graphs.
    B
  • DocsMint
    Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools.
    A