Codesearch MCP server
io.github.SK-DEV-AI/codesearch·v1.0.1·1 starsCode, package, docs, paper and vulnerability search. 17 tools, keyless lanes.
1 stars176 downloads/wk
Reviews
Write oneNobody has reviewed Codesearch yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Codesearch tools (17)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
analyzeDeep repo analysis: parallel-fetch GitHub metadata + SearchCode code quality + DeepWiki architecture + CodeWiki sections in one call. Start here for unfamiliar repos before surgical wiki/searchcode calls. Accepts GitHub URLs or owner/repo strings. May take 10-15s (parallel API calls). e.g. analyze(repository='sst/opencode')
code_filesList files in an indexed dependency by package-scoped path (e.g. npm:express/src/). PkgSeer + jsDelivr; indexes npm/pypi/crates ONLY (github: specs rejected). e.g. code_files(spec='npm:express')
code_readRead a file from an indexed dependency by package-scoped path. PkgSeer + jsDelivr; indexes npm/pypi/crates ONLY (github: specs rejected). e.g. code_read(spec='npm:express', path='src/index.js')
code_searchSearch code, docs, and symbols across indexed dependencies and public repositories. Package scope (npm:express, pypi:requests) via PkgSeer; global public-code search via Sourcegraph (keyless). Supports qualifiers like kind:, category:, lang:. e.g. code_search(query='handleAuth', target='npm:express')
docsDocumentation operations. Default action runs smart fallback (ReadTheDocs→DevDocs→llms.txt→Context7, quota-free sources first). After finding docs, use fetch(url) to read full pages or devdocs_fetch_content for structured content. e.g. docs(query='authentication', library='express')
enrichFetch full content for a list of search results, deduplicate, and rerank by relevance. Give it results from any search tool plus the original query. e.g. enrich(query='rust async', results=[{'url':'...','title':'...'}])
hnHacker News: search, item detail, user profile, or story lists (top/new/best/ask/show). Use for tech-community discussion and sentiment; for resolved Q&A use so_search. e.g. hn(query='rust', tags='story', min_points=50)
papersAcademic papers from Semantic Scholar, CORE API, and arXiv. Prefer action=search for topic queries (multi-source S2→arXiv→OpenAlex→CORE fallback); arxiv_search is single-source and rate-limited. e.g. papers(query='transformer attention', fields_of_study='Computer Science')
pingLightweight connectivity check — verifies internet and key API endpoints are reachable. Use before expensive calls when connectivity is uncertain. No params needed. e.g. ping()
pkgPackage intelligence: info (composite metadata — Libraries.io + Sonatype + PkgSeer), changelog (release notes), upgrade_review (vulns+changelog+deps diff between versions), files (list source files), read (read a source file). For raw single-source registry queries (npm versions, crates categories), use `search_package` instead. e.g. pkg(name='express', action='info')
search_allUnified search across 14+ sources with embedding dedup and reranking. Use for broad multi-source discovery; for surgical single-source work call so_search/hn/papers/code_search directly. e.g. search_all(query='rust async runtime', language='rust')
search_librariesLibraries.io dependency metadata and source rank. Use to compare dependency candidates or find the repo behind a package; for registry versions/vulns use search_package/pkg/vulns. e.g. search_libraries(name='lodash', platform='npm')
search_packageRaw package registry queries (npm/PyPI/crates + deps.dev). Use for fast single-source lookups. For composite intelligence (Libraries.io + Sonatype vulns), use `pkg` instead. e.g. search_package(name='express', registry='npm')
searchcodePer-repo code intelligence via SearchCode (free, no auth). Use analyze for instant repo overview (languages, complexity, tech stack, credentials), search for searching code within a repo, findings for code quality issues, file_tree to list files, or get_file to read a file. No rate limits. e.g. searchcode(action='analyze', repository='https://github.com/expressjs/express')
so_searchStack Overflow: Stack Exchange API (free, 300 req/day, resolved/accepted answers with score/tags) or SOFA (Stack Overflow for Agents, beta, agent-contributed content with trust scores, requires SOFA_KEY env). Use stackexchange for authoritative resolved answers, sofa for fresher agent-contributed content. e.g. so_search(query='python async', tags='python', accepted=true)
vulnsSonatype Guide + OSV.dev fallback: scan packages, vulnerability details, latest version, or license analysis by PURL. scan needs platform+name+version (or coordinates) — on Sonatype 401/429/quota errors it falls back to keyless OSV.dev automatically. detail accepts Sonatype ids, GHSA-* (GitHub Advisory enrichment), or CVE-* ids. latest_version/license need purl. e.g. vulns(action='scan', name='lod
wikiRepo architecture and wiki via DeepWiki + CodeWiki. For single-repo queries use owner+repo; for multi-repo questions pass repos (array of owner/repo strings, max 10). e.g. wiki(owner='torvalds', repo='linux', question='How does the scheduler work?')
Public scan report
scanner v0.1.10 · 2026-10-24 · same rubric, same numbers if you re-run it
- Code scan37 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 qualitystatic API keys via environment variables6/15
- Maintenancelast push 1 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Codesearch compares
Against every graded Productivity MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 83/100
- higher than 60% of 1,299 Productivity servers
- Tools
- 17
- the typical Productivity server has 7
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 1
- more than 50% of 854 Productivity servers
- Downloads a week
- 176
- more than 70% of 427 Productivity servers with a package
What its tools let an agent do: 17 read
Install Codesearch in Claude Code, Cursor or VS Code
claude mcp add codesearch -- uvx skdev-codesearch-mcp
What the publisher says
From the Codesearch repository's README, as published. We do not edit it. Read it on GitHub
codesearch MCP Server
mcp-name: io.github.SK-DEV-AI/codesearch
· npx skills add SK-DEV-AI/skills
Code, package, docs, and paper search MCP server. Per-package source navigation (npm/PyPI/crates), per-repo intelligence (GitHub URL or owner/repo), Q&A communities, vulnerability data, documentation, and academic papers — with embedding dedup and a local cross-encoder reranker.
Tools (17)
- analyze — Start here for unfamiliar repos: GitHub metadata + code quality + wiki architecture in one call (10–15s).
- searchall** — Broad multi-source discovery (Context7, GitHub, DeepWiki, CodeWiki, SO, HN, Libraries.io, npm, DevDocs, Semantic Scholar, Tavily…). For surgical single-source work call the tool below directly.
- codesearch** — Search code/docs/symbols across indexed dependencies (target=npm:express). npm/PyPI/crates only — for GitHub repos use searchcode or analyze.
- codefiles / coderead — List files / read a file in an indexed dependency by package spec.
- searchcode — Per-repo intelligence: analyze (overview), search (code within the repo), findings (quality issues), filetree, getfile. Needs repository for every action. Free, no auth.
- wiki — Repo architecture Q&A via DeepWiki + CodeWiki. Single repo (owner+repo) or up to 10 repos (repos).
- searchpackage** — Raw registry queries: versions, dist-tags, deps.dev graphs, advisories (version='latest' OK). For composite intelligence use pkg.
- pkg — Composite package intelligence: metadata, changelog, upgrade review (vulns + changelog + deps diff), file list/read.
- searchlibraries** — Libraries.io metadata and source rank. Compare dependency candidates, find the repo behind a package.
- vulns — Sonatype Guide + keyless OSV.dev fallback: scan (needs platform+name+version), detail (needs vulnid; enriched with NVD CVSS/CWE/references), latestversion/license (need purl).
- docs — Docs with smart fallback (Context7 → ReadTheDocs → llms.txt → DevDocs); then fetch(url) or devdocsfetchcontent for full pages.
- sosearch — Stack Overflow: stackexchange (authoritative resolved answers) or sofa (fresher agent content, needs SOFAKEY).
Setup
Requires Python 3.14+.
python3 -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
cp run.example run # fill in your API keys (run is gitignored — never commit it)
chmod +x runPoint your MCP client at run (stdio):
{ "codesearch": { "command": "/path/to/codesearch/run" } }API keys (run)
Install from PyPI
pip install skdev-codesearch-mcp # core install, small
pip install skdev-codesearch-mcp[all] # + browser/OCR/extract extras (multi-GB)The codesearch-mcp console script speaks MCP over stdio:
{ "codesearch": { "command": "codesearch-mcp" } }Docker
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Codesearch: common questions
- Is Codesearch MCP server safe?
- Mostly: it is graded B (83/100). Read the Codesearch safety report
- How do I install Codesearch?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Codesearch need an API key?
- Yes. The registry entry asks for
GROQ_API_KEYS,TAVILY_KEYS,NV_KEY,SE_KEYand 1 more. - Is Codesearch maintained?
- The last commit was 12 days ago (2026-10-23). The latest release is v1.0.1.
- What can I use instead of Codesearch?
- Servers from other publishers that do the same job: Mdma MCP server, Context7 MCP server and Svelte MCP server.
- How does Codesearch compare with other Productivity MCP servers?
- safety score 83/100 (higher than 60% of 1,299 Productivity servers); tools 17 (the typical Productivity server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Codesearch
Same job from other publishers: the closest match first, then the best rated.
- MdmaMCP server for MDMA — exposes spec, prompts, docs, and package metadata to AI assistants.not reviewedGrowingA
Context7Up-to-date docs for AI agentsnot reviewedWidely usedA- Svelte MCPThe official Svelte MCP server providing docs and autofixing tools for Svelte developmentnot reviewedEstablishedA
SvGridChecks AI-written SvGrid code against the real API, plus version-pinned Svelte 5 grid docs.not reviewedEstablishedA- Coolify46 optimized tools for managing Coolify infrastructure, diagnostics, and docs searchnot reviewedEstablishedB