Sema MCP Server

MCP tools for Sema — eval, compile, build, format, and docs for a Lisp with LLM primitives.

Local serverstdioGo

What is the Sema MCP server?

If you already use Sema, the sema mcp server is the piece that lets your assistant work with it directly. MCP tools for Sema — eval, compile, build, format, and docs for a Lisp with LLM primitives.

What the server does

A Lisp where LLM agents are language primitives, not an SDK —

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • Multi-provider — swap between Anthropic, OpenAI, Gemini, Ollama, any OpenAI-compatible endpoint, or define your own provider in Sema
  • Pipeline-ready — response caching, fallback chains, rate limiting, retry with backoff, text chunking, prompt templates, vector store, and a persistent KV store
  • Cost-aware — built-in budget tracking with a bundled pricing snapshot (models.dev), updated per release
  • Observable — every LLM/agent run is auto-traced with OpenTelemetry (GenAI semantic conventions): tokens, cost, latency, and the full invoke_agent → chat →
  • Embeddablea Rust crate with a builder API, or @sema-lang/sema to run
  • Developer-friendly — REPL with tab completion, structured error messages with hints, and 50+ example programs
  • Single-threaded — Rc-based, no cross-thread sharing of values
  • Provider — Chat
  • Anthropic — ✅
  • OpenAI — ✅
  • Ollama — ✅
  • Groq — ✅

Installation

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

Where it fits

Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Sema's toolset — Multi-provider, Pipeline-ready, Cost-aware and 11 more — is a fair guide to whether it matches your workflow. It is maintained by com.sema-lang; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Sema.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
Multi-providerswap between Anthropic, OpenAI, Gemini, Ollama, any OpenAI-compatible endpoint, or define your own provider in Sema
Pipeline-readyresponse caching, fallback chains, rate limiting, retry with backoff, text chunking, prompt templates, vector store, and a persistent KV store
Cost-awarebuilt-in budget tracking with a bundled pricing snapshot ([models.dev](https://models.dev)), updated per release
Observableevery LLM/agent run is auto-traced with OpenTelemetry (GenAI semantic conventions): tokens, cost, latency, and the full invoke_agent → chat → execute_tool tree, exportable to Jaeger, Grafana, Datadog, Langfuse, Arize Pho
Embeddable[a Rust crate](https://crates.io/crates/sema-lang) with a builder API, or [@sema-lang/sema](https://www.npmjs.com/package/@sema-lang/sema) to run Sema client-side in JS via WebAssembly
Developer-friendlyREPL with tab completion, structured error messages with hints, and 50+ example programs
Single-threadedRc-based, no cross-thread sharing of values
ProviderChat
Anthropic
OpenAI
Ollama
Groq
xAI
Mistral

Example prompts to try

  • Use Sema to Multi-provider.
  • Use Sema to Pipeline-ready.
  • Use Sema to Cost-aware.

Frequently asked questions

It connects Sema to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (Multi-provider, Pipeline-ready, Cost-aware, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Sema directly.