MCP servers · ataraxy-labs

sem: entity-level code intelligence for AI agents via MCP

An MCP server exposing sem's entity-level code intelligence to AI agents, covering semantic diffs, impact analysis, search, project checks and review certificates.

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

sem is a semantic version control tool built on Git. It parses code with tree-sitter and treats functions, classes and methods as entities, so diffs report which entities changed rather than line ranges. Through the sem mcp command, the same operations are available to agents as MCP tools: finding and searching entities, impact analysis, running project checks, and generating review certificates for commit ranges.

An agent would use it to locate a definition and its callers, to see which dependents and tests a change reaches, to run the project's compiler, type checker, linter and tests with a pass, fail or undecided verdict, or to list what a human should review in a commit range. It works in any Git repository without setup, and also compares arbitrary files outside Git.

Installation is available through Homebrew, winget, Scoop, npm, cargo, a source build or Docker. Entity caches are stored outside the repository, and the cache location can be overridden with SEM_CACHE_DIR. Checks detect the checkers used by each project and rerun only the files a change can affect, where that gives the same result.

Limitations and requirements

Works in Git repositories; outside Git it is limited to arbitrary file comparison. Cloud-backed queries are opt-in per repository. The sem binary name conflicts with the sem binary shipped by GNU Parallel, so sem --version should be used to confirm which one is running. Building from source requires Rust. With Bun, the package must be trusted so its postinstall script can download the binary. sem check reports 2 when there is nothing to check.

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
    io.github.Ataraxy-Labs/sem

    Entity-level code intelligence: semantic diff, impact analysis, blame, and context for AI agents

    v0.30.1
    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
sem: entity-level code intelligence for AI agents via MCP | AI Gate Discover