RUNN

- Python 3.10+
- Runn API key (RUNN_API_KEY)

python3 -m venv .venv source .venv/bin/activate python -m pip install --upgrade pip pip install -r requirements.txt

py -m venv .venv .\\.venv\\Scripts\\Activate.ps1 py -m pip install --upgrade pip pip install -r requirements.txt

py -m venv .venv .\\.venv\\Scripts\\activate.bat py -m pip install --upgrade pip pip install -r requirements.txt

brew install python@3.11 python3 -m venv .venv source .venv/bin/activate python -m pip install --upgrade pip pip install -r requirements.txt

RUNN_API_KEY=LIVE_... python3 mcp_runn_server.py --transport stdio

$env:RUNN_API_KEY="LIVE_..." py mcp_runn_server.py --transport stdio

RUNN_API_KEY=LIVE_... python3 mcp_runn_server.py --transport stdio

RUNN_API_KEY=LIVE_... python3 mcp_runn_server.py --transport streamable-http

$env:RUNN_API_KEY="LIVE_..." py mcp_runn_server.py --transport streamable-http

RUNN_API_KEY=LIVE_... python3 mcp_runn_server.py --transport streamable-http

docker run --rm -e RUNN_API_KEY=LIVE_... -p 8000:8000 runn-mcp-server

docker run --rm -e RUNN_API_KEY=LIVE_... -p 8000:8000 runn-mcp-server

docker run --rm -e RUNN_API_KEY=LIVE_... -p 8000:8000 runn-mcp-server

The GitHub Actions workflow publishes to:

docker pull ghcr.io/gemini2026/runn-mcp-server:main docker run --rm -e RUNN_API_KEY=LIVE_... -p 8000:8000 ghcr.io/gemini2026/runn-mcp-server:main

docker pull ghcr.io/gemini2026/runn-mcp-server:main docker run --rm -e RUNN_API_KEY=LIVE_... -p 8000:8000 ghcr.io/gemini2026/runn-mcp-server:main

docker pull ghcr.io/gemini2026/runn-mcp-server:main docker run --rm -e RUNN_API_KEY=LIVE_... -p 8000:8000 ghcr.io/gemini2026/runn-mcp-server:main

{ "mcpServers": { "runn": { "command": "/path/to/python3", "args": [ "/path/to/mcp_runn_server.py", "--transport", "stdio" ], "env": { "RUNN_API_KEY": "<YOUR_API_KEY>" } } } }

{ "mcpServers": { "runn": { "command": "C:\\\\Python311\\\\python.exe", "args": [ "C:\\\\path\\\\to\\\\mcp_runn_server.py", "--transport", "stdio" ], "env": { "RUNN_API_KEY": "<YOUR_API_KEY>" } } } }

- list_projects— returns{id, name}pairs.
- list_people— returns{id, name, email}by default (setfull=truefor raw objects).
- billable_hours— aggregates billable hours grouped by project/person/month.
- list_clients— list clients (raw API objects).
- list_assignments— list assignments (raw API objects).
- list_assignments_by_person— assignments for a person, optional date range.
- list_assignments_by_project— assignments for a project, optional date range.
- list_assignments_by_role— assignments for a role, optional date range.
- list_assignments_by_team— assignments for a team’s people, optional date range.
- list_actuals— list actuals (raw API objects).
- list_actuals_by_date_range— actuals in a date range, optional person/project filters.
- list_actuals_by_person— actuals for a person, optional date range.
- list_actuals_by_project— actuals for a project, optional date range.
- list_actuals_by_role— actuals for a role, optional date range.
- list_actuals_by_team— actuals for a team’s people, optional date range.
- list_roles— list roles (raw API objects).
- list_roles_by_person— roles that include a person.
- list_skills— list skills (raw API objects).
- list_skills_by_person— skills for a person with levels + names.
- list_teams— list teams (raw API objects).
- list_people_by_team— people in a team (optionally include archived).
- list_people_by_skill— people who have a skill (optional min level).
- list_people_by_tag— people with a tag (by id or name).
- list_people_by_manager— people managed by a manager id.
- list_rate_cards— list rate cards (raw API objects).
- list_rate_cards_by_project— rate cards that include a project.
- runn_request— call any Runn API endpoint (GET/POST/PATCH/PUT/DELETE).

{ "method": "GET", "path": "/projects", "paginate": true }

Filter-specific tools (e.g.,list_assignments_by_person) fetch list endpoints and apply filters client-side.

RUNN_API_KEY=LIVE_... python3 mcp_runn_server.py --transport streamable-http

curl -s http://localhost:8000/api \ -H "Content-Type: application/json" \ -d '{ "tool": "list_actuals_by_person", "args": { "person_id": 123, "start": "2025-01-01", "end": "2025-01-31" } }' | jq

curl -s http://localhost:8000/api \ -H "Content-Type: application/json" \ -d '{ "tool": "runn_request", "args": { "method": "GET", "path": "/projects" } }' | jq

stdio transport (Claude/Desktop or script)

printf '{"tool":"list_projects"}' | RUNN_API_KEY=LIVE_... python3 mcp_runn_server.py --transport stdio

Claude will read the JSON response from stdout, just like any MCP client.

docker run --rm -e RUNN_API_KEY=LIVE_... -p 8000:8000 runn-mcp-server

Connect via the HTTP examples above or switch to stdio by appending--transport stdioon the Docker command.

runn_reports.pycan export billable hours grouped by project/person/month.

RUNN_API_KEY=LIVE_... python3 runn_reports.py --start 2025-01-01 --end 2025-12-31 --output billable.csv

- CI runs on every push and pull request tomain.
- CD publishes a GitHub Release when you push a tag likev0.1.0.

Magica is your all-in-one AI platform, offering 2500+ cutting-edge tools under a single subscription.

Turn your Make scenarios into callable tools for AI assistants.

Dynamically search and call tools using UnifAI Network

Connect your AI Agents to 8,000 apps instantly.

Connect AI assistants to Automatisch for workflow automation.

Unified MCP gateway that loads 150+ AI tools into Claude Desktop via a single Docker command on Windows. Routes tool calls across specialized servers (Business Intelligence, API Hub, Content Automation, Intelligence) with centralized logging and governance. Built for teams without dedicated platform engineers.

Connect AI assistants directly to the HiveFlow automation platform.

A hub server that connects to and manages other MCP servers.

Connect your agent to 700+ apps (Gmail, Slack, Stripe, Shopify, HubSpot, Notion, Linear) through one MCP server with four tools and OAuth sign-in.

Connects AI agents to the SS&C Next Generation REST API to automate business processes.