MCP - any client

Standard protocol, zero lock-in

Cognetivy exposes a full MCP server via cognetivy mcp. Any MCP-compatible coding agent can connect to it: no proprietary format, no vendor lock-in. Tools map one-to-one to the CLI (workflow, run, event, collection, node-result). Install Cognetivy globally so the cognetivy command is on your PATH where the client runs.

Prerequisites

Install Cognetivy globally so the MCP server is available on your PATH:

npm install -g cognetivy

Then initialise a workspace in your project (or the directory that will contain .cognetivy/):

npx cognetivy

Connect your agent

Add the Cognetivy MCP server to your agent’s config. The config location varies by client (e.g. Cursor: Settings → MCP or .cursor/mcp.json; Claude: MCP config file). The server definition is always:

{
  "mcpServers": {
    "cognetivy": {
      "command": "cognetivy",
      "args": ["mcp"]
    }
  }
}

Workspace not in your project root?

Pass the workspace path explicitly so the server uses the correct .cognetivy/ directory:

"args": ["mcp", "--workspace", "/path/to/project"]

Supported platforms

The Cognetivy installer and MCP server work with any MCP-compatible client. Below are agents the installer can target (skills and/or MCP). Icons from Simple Icons where available.

Claude Code

Full agent skills + MCP

Cursor

Skills + MCP server

OpenClaw

Agent skill + MCP

GitHub Copilot

MCP or Agent Skills bundle

Gemini CLI

MCP or Agent Skills bundle

OpenAI Codex

MCP or Agent Skills bundle

Amp

MCP or Agent Skills bundle

Cursor Agent CLI

MCP or Agent Skills bundle

OpenCode

MCP or Agent Skills bundle

Factory Droid

MCP or Agent Skills bundle

Qwen Code

MCP or Agent Skills bundle

MCP - any client

Standard protocol

For Cursor, Claude Code, and OpenClaw we provide dedicated setup guides (agent skills + MCP). For the others, add the MCP server block above to the client’s MCP configuration; the installer can also install the Agent Skills bundle into a skills/ directory where supported.

Available MCP tools

Once connected, your agent has access to the full Cognetivy toolset. Each tool corresponds to a CLI command; parameters match the CLI (e.g. run_id, node_id, collection_kind).

workflow_get

Get the current workflow version

workflow_list

List all workflows in the workspace

workflow_set

Set a workflow version from JSON

run_start

Start a new run with an input file

run_status

Get run state and next step hint

run_step

Advance the run: start or complete a node

run_complete

Mark a run as completed

event_append

Append an event to a run

collection_get

Get collection items for a run + kind

collection_append

Append an item to a collection

collection_schema_get

Get the collection schema for a workflow

node_result_list

List node results for a run

Create your first workflow Full docs on GitHub