Skip to main content
Glama

mistral-vibe-mcp

An MCP stdio server that wraps the Mistral Vibe CLI (vibe / mistral-vibe) so any MCP client — Claude Desktop, Codex, Cursor, etc. — can drive the Vibe coding agent programmatically.

This is a clean-room implementation under the MIT license. It is inspired by the idea of an earlier vibe-mcp project but shares no code with it.

Tools

Tool

Purpose

vibe_run

Start a new Vibe session with a prompt in a project directory.

vibe_resume

Continue the last session (--continue) or resume a specific one (--resume SESSION_ID).

vibe_manage

status (installed? version), install, or update Vibe via uv.

vibe_run

Field

Type

Notes

prompt

string (required)

Instruction for the agent.

project_dir

string

Working dir. Defaults to the server cwd.

max_turns

integer

--max-turns (recommended).

max_tokens

integer

--max-tokens.

max_price

number

--max-price (indicative, not a hard budget).

time_limit

integer

--time-limit (seconds).

model

string

--model alias.

agent

enum

ask | accept-edits | smart-approve | auto-approve.

enabled_tools

string[]

--enabled-tools (repeatable; globs / re: regex).

disabled_tools

string[]

--disabled-tools (repeatable).

auto_approve

boolean

--auto-approve/--yolo. Default false.

worktree

string|boolean

--worktree [name].

trust

boolean

--trust (temporary trust for cwd).

output

enum

json (default) | text | streaming.

vibe_resume

Same fields as vibe_run, plus the ones below. prompt is optional: when omitted, the server sends "Continue where you left off." (Vibe only runs headless when given a prompt) and says so in notes.

Field

Type

Notes

session_id

string

Resume a specific session (--resume). Partial ids are accepted by Vibe.

continue

boolean

Continue the last session for the dir (--continue). Default when no session_id.

If both session_id and continue are given, session_id wins and a note is returned.

vibe_manage

Field

Type

Notes

action

enum (required)

status | install | update. install/update run uv tool install --upgrade mistral-vibe.

Result shape

Each vibe_run / vibe_resume call returns a human summary line plus a JSON block:

{
  "ok": true,
  "exitCode": 0,
  "exitClass": "finished",
  "timedOut": false,
  "sessionId": "28610fb0-6989-bbd5-220f-4bd5b1a0acb0",
  "summary": { "cost": 0.012, "tokens": 2048 },
  "outcome": "completed",
  "stopReason": "end_turn",
  "output": { "...": "parsed vibe --output json, or null" },
  "text": "raw stdout, only when output is not JSON (e.g. output: \"text\")",
  "error": "Vibe's error message, when the run failed",
  "notes": ["..."],
  "stderr": "..."
}

sessionId, summary, outcome, stopReason and error come from the export.json Vibe writes to a private temporary --output-dir on every exit (deleted afterwards); stdout is only scraped as a fallback.

exitClass maps Vibe's documented exit codes: 0 finished, 1 start-or-config-error, 2 api-or-runtime-error, 3 stopped-early.

Related MCP server: cursor-agent-bridge

Prerequisites

  • Node 20+

  • Mistral Vibe CLI installed:

    uv tool install --upgrade mistral-vibe

    (Need uv? See the uv install guide.) You can also run vibe_manage { "action": "install" } from any MCP client.

If the vibe binary lives somewhere non-standard, set VIBE_BIN to its path.

Install & build

git clone https://github.com/sohampatwardhan/mistral-vibe-mcp.git
cd mistral-vibe-mcp
npm install
npm run build

The server entrypoint is dist/index.js (also exposed as the mistral-vibe-mcp bin).

MCP client configuration

All clients launch the server over stdio with node /abs/path/to/dist/index.js.

Claude Desktop

claude_desktop_config.json:

{
  "mcpServers": {
    "mistral-vibe": {
      "command": "node",
      "args": ["/abs/path/to/mistral-vibe-mcp/dist/index.js"]
    }
  }
}

Codex

~/.codex/config.toml:

[mcp_servers.mistral-vibe]
command = "node"
args = ["/abs/path/to/mistral-vibe-mcp/dist/index.js"]

Cursor

.cursor/mcp.json (project) or ~/.cursor/mcp.json (global):

{
  "mcpServers": {
    "mistral-vibe": {
      "command": "node",
      "args": ["/abs/path/to/mistral-vibe-mcp/dist/index.js"]
    }
  }
}

Optional env (add an "env": { ... } block to any of the above):

  • VIBE_BIN: path to vibe if it isn't on PATH for the client process.

  • VIBE_MCP_TIMEOUT_SECONDS: hard timeout for a run without time_limit (default 1800). With time_limit, the server lets Vibe stop itself and only kills it 60s after that.

Example calls

// vibe_run
{ "prompt": "Add input validation to the login form", "max_turns": 6, "agent": "accept-edits" }

// vibe_resume - specific session
{ "session_id": "abc123", "prompt": "now add tests" }

// vibe_resume - continue last
{ "continue": true, "prompt": "keep going" }

// vibe_manage
{ "action": "status" }

Development

  • npm test runs the unit tests (no Vibe binary or network needed).

  • npm run build typechecks and emits dist/.

  • npm run dev runs the compiler in watch mode.

Tests cover the pure core (CLI argument building, output and export.json parsing), the process runner (timeouts, closed stdin) against real child processes, and the tool handlers end to end against a fake vibe script (test/fixtures/fake-vibe.mjs).

See CONTRIBUTING.md for the PR workflow and code rules, and CHANGELOG.md for what changed in each version.

How it works

MCP client <-> (stdio/JSON-RPC) <-> index.ts
                                      |- tools.ts  (schemas + dispatch)
                                      |- args.ts   (pure argv builders)
                                      |- parse.ts  (pure output parsing)
                                      |- runner.ts (spawn vibe)
                                      |- manage.ts (status/install/update)

The server never builds shell strings; it spawns vibe with an argv array, so prompts and tool names can't inject shell commands.

Agent Skills

This repo ships Agent Skills so an agent can learn how to drive these MCP tools. Install them with the skills CLI:

# all skills in this repo
npx skills add sohampatwardhan/mistral-vibe-mcp

# a specific skill
npx skills add sohampatwardhan/mistral-vibe-mcp --skill vibe-run

Skills live under skills/<name>/SKILL.md (the standard npx skills discovery path):

Skill

Teaches

mistral-vibe

Umbrella overview + when to load the others.

vibe-run

Starting a new session: prompt, project_dir, guardrails, agent profiles, auto_approve caution.

vibe-resume

Resume (session_id) vs continue precedence and when to use each.

vibe-manage

status/install/update via uv, and VIBE_BIN.

These skills teach how to use this server's tools; they are not a copy of Vibe's own docs.

License

MIT - see LICENSE.

Session and flag behavior is based on the current Vibe CLI programmatic docs: https://docs.mistral.ai/vibe/code/cli/work-with-cli.

Available Tools

3 tools
vibe_manageA

Operational helper for the Vibe CLI: status (installed? version), install, or update via uv tool install --upgrade mistral-vibe.

Inputs: action (required).

vibe_resumeA

Continue a previous Vibe session. Provide session_id to resume a specific session (--resume), or continue:true (default when no session_id) to continue the last session for the directory.

Inputs: agent, model, trust, output, +12 more.

vibe_runB

Start a new Mistral Vibe coding-agent session with a prompt in a project directory. Returns parsed JSON output, session id, exit classification, and a cost/turn summary when available.

Inputs: prompt (required), agent, model, trust, +10 more.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool targets a distinct lifecycle phase: starting a session (vibe_run), continuing one (vibe_resume), and CLI maintenance (vibe_manage). There is no overlap — run vs resume is clearly separated by whether a new prompt/session or an existing session is involved.

    Naming Consistency5/5

    All three tools use a consistent vibe_<verb> snake_case pattern (vibe_run, vibe_resume, vibe_manage). Names are short, readable, and predictable.

    Tool Count4/5

    Three tools is on the thin side but well-matched to a focused CLI wrapper: launch, continue, maintain. Nothing extraneous, though a couple more operations could reasonably be added.

    Completeness4/5

    The core agent-session lifecycle (start, resume, install/update/status) is covered, which handles the main workflows. Minor gaps exist — no session listing, cancellation/kill of a running session, or history retrieval — but agents can work around these via run/resume output.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables MCP clients to spawn and control Codex CLI and Claude Code sessions on the host machine, with session management and filesystem access.
      4
      MIT
    • A
      license
      Not graded
      quality
      A
      maintenance
      Enables any MCP-compatible client to run reusable, Markdown-defined coding agents (such as reviewers, test writers, or investigators) through a configurable coding CLI backend, returning results into the same conversation. Agent definitions and backend/model settings can be shared across clients, and sessions can persist across multiple calls for longer work.
      127 npm
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables MCP clients to submit code review tasks to locally installed AI coding CLI agents, continue sessions, query progress, handle stop requests, and retrieve results and artifacts using the user's own authenticated accounts.
      1
      Apache 2.0