Contextweaver MCP server
io.github.wchiway/contextweaver·v1.5.4·2 starsSemantic code retrieval engine with hybrid search, context expansion, and 40+ language support.
2 stars51 downloads/wk
Reviews
Write oneNobody 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 postsRead from the package source without running it. The installed server may list more.
codebase-retrievalIMPORTANT: 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-referencesFind 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-definitionFind 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-filesList 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-symbolsList 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
statsShow 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
- 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
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
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.
- VexorA semantic search engine for files and code.not reviewedEstablishedB
- M3 MemoryLocal-first, cloud-friendly memory — 100+ tools, 99.2% LongMemEval-S retrieval@8, hybrid search.not reviewedEstablishedA
- ArxivSearch arXiv papers, download full text, semantic search, citation graphs, and alerts via MCP.not reviewedWidely usedA
- SocraticodeMCP server for enterprise local codebase indexing, semantic search, and code dependency graphs.not reviewedEstablishedB
DocsMintCloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools.not reviewedEstablishedA