mistral-vibe-mcp
Wrap the Mistral Vibe CLI as an MCP stdio server so clients can run, resume, and manage Vibe coding-agent sessions.
Start a new Vibe session with a required prompt via
vibe_run, optionally settingproject_dir, turn/token/price/time limits, model, agent profile, tool allow/deny lists, auto-approval, worktree, trust, and output format.Continue the last session or resume a specific session via
vibe_resume, with an optional follow-up prompt and the same run options.Check Vibe installation status/version, install it, or update it via
vibe_manageusinguv.Receive structured results including parsed output, session ID, exit classification, outcome, stop reason, cost/token summary, notes, errors, and stderr.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mistral-vibe-mcp Start a Vibe session to add tests for the login form"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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 |
| Start a new Vibe session with a prompt in a project directory. |
| Continue the last session ( |
|
|
vibe_run
Field | Type | Notes |
| string (required) | Instruction for the agent. |
| string | Working dir. Defaults to the server cwd. |
| integer |
|
| integer |
|
| number |
|
| integer |
|
| string |
|
| enum |
|
| string[] |
|
| string[] |
|
| boolean |
|
| string|boolean |
|
| boolean |
|
| enum |
|
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 |
| string | Resume a specific session ( |
| boolean | Continue the last session for the dir ( |
If both session_id and continue are given, session_id wins and a note is returned.
vibe_manage
Field | Type | Notes |
| enum (required) |
|
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 runvibe_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 buildThe 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 tovibeif it isn't on PATH for the client process.
VIBE_MCP_TIMEOUT_SECONDS: hard timeout for a run withouttime_limit(default 1800). Withtime_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 testruns the unit tests (no Vibe binary or network needed).npm run buildtypechecks and emitsdist/.npm run devruns 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-runSkills live under skills/<name>/SKILL.md (the standard npx skills discovery path):
Skill | Teaches |
| Umbrella overview + when to load the others. |
| Starting a new session: prompt, |
| Resume ( |
|
|
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 toolsvibe_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
Scored across 3 tools
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.
All three tools use a consistent vibe_<verb> snake_case pattern (vibe_run, vibe_resume, vibe_manage). Names are short, readable, and predictable.
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.
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
Related MCP Connectors
Start and manage Reason cloud coding agents, projects and sessions from any MCP client.
Open-source vibe coding hosting over MCP: your agent builds, previews and publishes web apps.
Project management shared by people and AI agents, with persistent project state through MCP.
Build, test, publish, and run Kovca workflows from AI agents over remote MCP.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables MCP clients to spawn and control Codex CLI and Claude Code sessions on the host machine, with session management and filesystem access.4MIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients like Claude Code to delegate coding tasks to the local Cursor Agent CLI, with persistent per-workspace sessions that resume across calls.12 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables 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 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables 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.1Apache 2.0