MCP servers · ahmeedgamil

semhood: AST-based semantic code search MCP server

An MCP server that searches code by intent, returning functions, methods and classes together with their call graph.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

semhood is an MCP server and semantic code search tool that parses source with Tree-sitter and indexes every function, method and class as its own chunk, with its signature and docstring attached. Queries are run as a hybrid of dense vectors and BM25 sparse retrieval. It supports Python, JavaScript, TypeScript, Java, Go, PHP, C#, Ruby, Rust and C++. Each result includes what the chunk calls and what calls it, and the get_chunk_context tool returns the body along with these callers and callees in one response.

It suits cases where keyword search misses code, for example when a developer asks how a behaviour is implemented and the source uses terse names or raw logic. An optional enrichment step uses an LLM or a code agent to write a logic summary and predicted developer questions for each chunk, stored as separate vectors. The enrichment is generated once and can be committed to git for the team to share. Incremental indexing with --changed re-indexes only the files touched by git diff. The MCP server is listed as working with Claude Desktop, Cursor, Cline, Continue, Kiro and Zed.

Setup needs Python 3.11 or later. By default it runs offline with a local embedding model and no API keys, and the first index downloads that model, about 420 MB, and caches it. Cloud embeddings from Voyage or OpenAI can be used instead. A background daemon keeps the embedding model loaded between searches. Each project gets its own index under ~/.semhood/indexes, and a single global configuration file is created at ~/.semhood/config.yaml.

Limitations and requirements

Requires Python 3.11 or later. The first indexing run downloads an embedding model of about 420 MB. Cloud embedding options require access to Voyage or OpenAI. LLM enrichment requires an LLM or a code agent.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    semhood

    AST-based semantic code search; results ship with their call graph (calls + callers).

    v0.1.0
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
hashicorp

Terraform MCP Server (HashiCorp)

HashiCorp's MCP server that gives an assistant current Terraform Registry information on providers, modules and policies, and can manage HCP Terraform workspaces.

1.6K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026
MCP servers
modelcontextprotocol

MCP reference servers

Seven small example servers maintained by the Model Context Protocol project: files, Git, web fetching, memory, time, step-by-step thinking and a test server.

92K GitHub starsSoftware development
Updated 18 Nov 2026
MCP servers
redis

Redis MCP Server

Redis's official MCP server that lets an AI assistant store, read and search data in a Redis database, including streams, JSON documents and vector indexes.

642 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
firecrawl

Firecrawl MCP Server (web search and scraping)

Firecrawl's MCP server that lets an AI assistant search the web, turn pages and PDFs into clean Markdown, crawl sites and interact with dynamic pages.

7.8K GitHub starsWeb, search & browserProductivity & automation
Updated 17 Nov 2026
semhood: AST-based semantic code search MCP server | AI Gate Discover