Skip to main content
Glama
Sign In
codesearch MCP Server

codesearch MCP Server

by SK-DEV-AI
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

codesearch MCP Server

mcp-name: io.github.SK-DEV-AI/codesearch

Companion agent skills: SK-DEV-AI/skills · 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).

  • search_all — 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.

  • code_search — Search code/docs/symbols across indexed dependencies (target=npm:express). npm/PyPI/crates only — for GitHub repos use searchcode or analyze.

  • code_files / code_read — 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), file_tree, get_file. 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).

  • search_package — 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.

  • search_libraries — 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 vuln_id; enriched with NVD CVSS/CWE/references), latest_version/license (need purl).

  • docs — Docs with smart fallback (Context7 → ReadTheDocs → llms.txt → DevDocs); then fetch(url) or devdocs_fetch_content for full pages.

  • so_search — Stack Overflow: stackexchange (authoritative resolved answers) or sofa (fresher agent content, needs SOFA_KEY).

  • hn — Hacker News discussion and sentiment (search, stories, items, users).

  • papers — Academic papers. Prefer action=search (S2 → arXiv → OpenAlex → CORE fallback chain); arxiv_search is single-source and rate-limited.

  • enrich — Fetch full content for a result list from any search tool, dedup + rerank.

  • ping — Connectivity check. Use before expensive calls when uncertain.

Related MCP server: Code Search MCP

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 run

Point your MCP client at run (stdio):

{ "codesearch": { "command": "/path/to/codesearch/run" } }

API keys (run)

Key

Used for

Required?

GITHUB_TOKEN

GitHub API (repo ops, higher rate limits)

Recommended

CONTEXT7_API_KEY

Context7 docs

Optional

TAVILY_KEYS

Tavily lane in search_all

Optional

S2_API_KEY

Semantic Scholar (1 rps dedicated vs shared anonymous pool)

Optional

SE_API_KEY / SOFA_KEY

Stack Exchange / Stack Overflow for Agents

Optional

LI_KEY

Libraries.io

Optional

OSS_TOKEN

Sonatype OSS Index

Optional

FIRECRAWL_KEYS

Firecrawl fallback

Optional

NV_KEY

NVIDIA embedding endpoint

Optional

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

docker build -t codesearch-mcp .
docker run --rm -i codesearch-mcp

Keys are passed at run time, never baked in: -e GROQ_API_KEYS=.... Heavy extras: docker build --build-arg EXTRAS="[all]" -t codesearch-mcp .

Notes

  • Reranker (optional, local): shared with the websearch server — one cross-encoder worker over a Unix socket. Without it, results return unranked; everything still works.

  • Caching: per-source file caches with TTLs; repeat queries are cheap.

  • Safety: all user-URL fetches are SSRF-validated (private-IP blocking + redirect-hop revalidation).

Available Tools

17 tools
analyzeA

Deep 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')

Inputs: repository (required).

code_filesA

List 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')

Inputs: spec (required), path_prefix.

code_readA

Read 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')

Inputs: path (required), spec (required).

code_searchA

Search 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')

Inputs: query (required), lang, limit, source, +1 more.

docsC

Documentation 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')

Inputs: fast, path, slug, query, +7 more.

enrichA

Fetch 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':'...'}])

Inputs: query (required), results (required), top_k, include_html, +1 more.

hnB

Hacker 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)

Inputs: action (required), tags, count, query, +6 more.

papersB

Academic 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')

Inputs: action (required), year, count, query, +8 more.

pingA

Lightweight connectivity check — verifies internet and key API endpoints are reachable. Use before expensive calls when connectivity is uncertain. No params needed. e.g. ping()

Inputs: no named parameters.

pkgA

Package 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')

Inputs: name (required), path, count, action, +6 more.

search_allA

Unified 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')

Inputs: query (required), repo, count, owner, +8 more.

searchcodeA

Per-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')

Inputs: action (required), path, query, category, +10 more.

search_librariesB

Libraries.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')

Inputs: name, repo, sort, count, +9 more.

search_packageA

Raw 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')

Inputs: name (required), action, version, registry, +3 more.

so_searchB

Stack 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)

Inputs: ids, page, site, sort, +15 more.

vulnsA

Sonatype 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='lodash', version='4.17.20')

Inputs: name, purl, action, version, +3 more.

wikiC

Repo 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?')

Inputs: action (required), repo, limit, owner, +5 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    B3.4/5.0

    Scored across 17 tools

    Disambiguation3/5

    The set has several overlapping clusters: code_files/code_read vs pkg(files/read) vs searchcode(file_tree/get_file), wiki vs analyze, and search_all vs direct source-specific searches. Descriptions usually clarify when to use each alternative, but an agent still faces non-trivial misselection risk among repo analysis, file reading, and package intelligence tools.

    Naming Consistency3/5

    Most names are lowercase and somewhat readable, but conventions are mixed: verb_noun names (search_all, code_search), noun-only names (wiki, docs, vulns, papers, pkg), and single verbs (analyze, enrich). The one-word searchcode also contrasts awkwardly with code_search, making the pattern less predictable.

    Tool Count4/5

    Seventeen tools are slightly above the ideal compact range, but the server genuinely spans many sources and operations: packages, code, docs, papers, HN, Stack Overflow, vulnerabilities, repo analysis, and enrichment. The count is reasonable for this broad scope, though a few overlapping tools could be consolidated.

    Completeness5/5

    The surface covers discovery, source reading, package metadata, dependency/vulnerability checks, documentation, academic papers, community discussion, repo analysis, file listing/reading, enrichment, and connectivity. No obvious domain-critical gap remains for a broad code-search/research MCP server.

    Maintenance

    ActivityActive
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers

    • MCP Indexer

      gkatechis
      A
      license
      Not graded
      quality
      D
      maintenance
      Enables semantic code search across multiple repositories using natural language queries. Provides intelligent code discovery, symbol lookups, and cross-repo dependency analysis for AI coding agents.
      MIT

    • Code Search MCP

      LLMTooling
      A
      license
      Not graded
      quality
      D
      maintenance
      Enables LLMs to perform high-performance code search and analysis across multiple languages using symbol indexing, regex text search, and structural AST pattern matching. It also provides tools for technology stack detection and dependency analysis with persistent caching for optimized performance.
      11
      MIT

    • Scout

      duguobao812718-wq
      A
      license
      B
      quality
      D
      maintenance
      Enables AI agents to perform comprehensive search across 27 search engines including web, academic, code, community, package managers, video, images, podcasts, and maps, with multi-modal support, caching, and security features.
      14
      MIT

    • CodeIntel MCP Server

      SecondLifes
      A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to perform hybrid code search, get explanations, analyze relations and impacts, retrieve context packs, and generate documentation across ~45 languages via 17 MCP tools, all powered by a local vector database and LLM.
      2
      Apache 2.0