dsmr-mcp: MCP Server para Common Lisp
fade/dsmr-mcp
Pair-programming com IA em sua imagem Lisp viva
Ver no GitHubServidor MCP que conecta um agente de IA diretamente a uma imagem Common Lisp em execução via Slynk, permitindo avaliação de código, inspeção de objetos vivos, edição estrutural e navegação de codebase no mesmo ambiente de desenvolvimento. Suporta três modos: attached (conexão a imagem existente), hermetic (pool de workers isolado) e auto (fallback inteligente).
Instalação
npx convez-ai fade/dsmr-mcp1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Desenvolvimento Common Lisp com assistência de IA em tempo real
- Debugging e inspeção de estado vivo com agentes
- Navegação e refatoração estrutural de codebases Lisp
- Testes e avaliação de código no contexto do projeto em execução
Veredito

Ferramenta especializada e bem-arquitetada para desenvolvedores Lisp que querem integração profunda entre agentes IA e imagens vivas. A abordagem image-first é inovadora, mas exige familiaridade tanto com Common Lisp quanto com MCP.
README
A tradução para o português deste README ainda está na fila.
#+TITLE: dsmr-mcp #+SUBTITLE: DeepSky Systems Model-context-Reagent for Common Lisp
=dsmr-mcp= is an [[https://modelcontextprotocol.io][Model Context Protocol]] (MCP) server that lets an AI agent work inside your live Common Lisp image. It connects an MCP client to a running Lisp over Slynk, so an agent can evaluate code, inspect live objects and threads, edit source structurally, run tests, navigate a codebase, and look up documentation — in the same image you are developing in.
- TL;DR — Quickstart
Prerequisites: SBCL, Quicklisp, and the source on your ASDF source path (e.g. under =~/SourceCode/lisp/=).
#+begin_src sh
1. Load and smoke-test the server (stdio transport, the default)
sbcl --non-interactive
--eval '(ql:quickload :dsmr-mcp)'
--eval '(dsmr-mcp:run)'
#+end_src
To attach to a Lisp image you are already running, start a Slynk listener in that image and point dsmr-mcp at it:
#+begin_src sh
DSMR_MODE=attached DSMR_SLYNK_ATTACH=127.0.0.1:4005
sbcl --non-interactive
--eval '(ql:quickload :dsmr-mcp)'
--eval '(dsmr-mcp:run)'
#+end_src
No image to attach to? Use =DSMR_MODE=hermetic= (a forked, crash-isolated SBCL worker pool) or =DSMR_MODE=auto= (attach if a listener is reachable, else hermetic). Then wire it into your MCP client (Claude Code and others) — see [[file:docs/configuration.org][Configuration]] for the client setup and the full environment-variable reference.
Driving more than one Lisp project from a single agent install? dsmr-mcp ships a per-project [[https://direnv.net][direnv]] =.envrc= so each project can point at its own image and port while the global MCP entry stays env-free — see [[file:docs/configuration.org::*direnv per-project setup][direnv per-project setup]].
Verify with a trivial =repl-eval= round trip: evaluating =(+ 1 2)= should return =3=.
- What it is
Lisp development is image-based: a developer builds up a running world of definitions, packages, threads, CLOS instances, and application state over a session. Conventional AI coding tools ignore that — they operate on files and a freshly spawned process, discarding the live context that makes Lisp productive.
=dsmr-mcp= takes the opposite stance, the attached-image-first thesis: the agent should work in the same running world the developer already inhabits, where a redefined function takes effect immediately, a live CLOS instance can be inspected, and a restart can be invoked. It is the Common Lisp analogue of a language server for an AI — a structured set of verbs over a live image.
The name is a backronym, expanding (at your convenience) To: DeepSky Systems Model-context-Reagent for Common Lisp.
- Intended use case
The intended use is a developer pair-programming with an AI agent in their own running Lisp. The developer starts their project image with a Slynk listener; dsmr-mcp attaches to it; the agent then has the same live, image-resident tools the developer has at the REPL. It is explicitly a single-operator, localhost developer tool — not a multi-tenant or hosted service.
Who uses it:
- A Common Lisp developer who wants an AI agent to work in their live image.
- An AI agent (Claude and others) acting as that developer's pair, via an MCP client.
The operator is the trust root: they already trust the agent to evaluate code in their image. See the [[file:docs/threat-model.org][threat model]] for the full posture — in short, =dsmr-mcp= is a trust-amplifier for an agent the operator already trusts, not a containment layer against a hostile one.
- What you get
- 28 verbs across REPL evaluation and build (=repl-eval=, =load-system=, =run-tests=), filesystem access (=fs-=), structural Lisp editing (=lisp-=), code intelligence (=code-find=, =code-describe=, =clgrep-search=, =clhs-lookup=, …), live-image inspection (=inspect-=), an LSP bridge (=lsp-=), hermetic operations (=pool-status=, =pool-kill-worker=), and project scaffolding (=project-scaffold=).
- Three transports: stdio (default), TCP, and Streamable HTTP (with a bundled bridge). Loopback-only by default.
- Three execution modes: attached, hermetic, and auto.
- A filesystem sandbox as the one enforced agent-facing control, structured logging, a reviewable threat model, and an operations runbook.
- Documentation
The full manual lives in [[file:docs/index.org][=docs/=]]:
- [[file:docs/introduction.org][Introduction]] — overview and the attached-image-first thesis.
- [[file:docs/installation.org][Installation & Build]] — prerequisites, loading, running, testing.
- [[file:docs/configuration.org][Configuration]] — environment variables, modes, transports, MCP-client wiring.
- [[file:docs/architecture.org][Architecture]] — how a request flows from client to image.
- [[file:docs/modes-and-transports.org][Modes & Transports]] — when to use each mode and transport.
- [[file:docs/tools.org][Tool reference]] — every verb, generated from the live registry.
- [[file:docs/operations.org][Operations & Runbook]] — health checks and field recipes.
- [[file:docs/threat-model.org][Threat model]] — trust boundaries and the STRIDE register.
- [[file:docs/release-notes.org][Release notes]].
- Status
v0.1.0 — first tagged release. See [[file:docs/release-notes.org][the release notes]].
- License
AGPL-3.0-or-later
© Brian O'Reilly / DeepSky Systems