Tools

Four tools covering the full workflow library lifecycle — discovery, retrieval, and creation for both permanent and temporary workflows:

workflow_list

List permanent workflows from the in-memory index.

• Optional category filter (case-insensitive substring match)
• Optional tag filter (AND match — all listed tags must be present)
• Set includeTools: true to surface the unique server/tool pairs used across each workflow's steps
• Temporary workflows are excluded; results sorted by name then version descending

workflow_get

Retrieve a complete workflow by name, including the global instructions document.

• Semver-aware: omit version to get the highest available match; specify a version for an exact lookup
• Returns the full workflow YAML structure with all steps and metadata
• Injects the global_instructions.md content as globalInstructions — apply these when executing the workflow; null when the file is absent
• Temporary workflows are accessible here even though excluded from workflow_list
• Template placeholders ({{input.foo}}, {{steps.X.output.Y}}) are returned verbatim — the server never interpolates them

workflow_create

Write a new permanent workflow to the library.

• Workflow stored at categories/<slugified-category>/<slugified-name>-workflow.yaml
• Rejects if name@version already exists — bump the version to create a new revision
• Server stamps created_date and last_updated_date automatically
• Index and snapshot rebuilt after write; filesystem watcher also fires (idempotent, debounced)

workflow_create_temp

Write a throwaway workflow to the temp/ directory.

• No conflict check — temp workflows are intentionally ephemeral and overwriteable
• Indexed and accessible via workflow_get but excluded from workflow_list results
• Useful for one-shot plans, short-lived scaffolding, or session-specific orchestration steps

Features

Built on @cyanheads/mcp-ts-core:

• Declarative tool definitions — single file per primitive, framework handles registration and validation
• Unified error handling — handlers throw, framework catches, classifies, and formats
• Pluggable auth: none, jwt, oauth
• Swappable storage backends: in-memory, filesystem, Supabase, Cloudflare KV/R2/D1
• Structured logging with optional OpenTelemetry tracing
• STDIO and Streamable HTTP transports

Workflow library:

• In-memory index keyed by name@version, built at startup from workflows-yaml/categories/ recursively
• Semver-aware lookup — latest version returned when version is omitted
• Filesystem watcher (Node.js fs.watch recursive) rebuilds the index on any add/change/remove; debounced to avoid thrash
• YAML validated at index time — invalid files are skipped and logged, never crash the server
• _index.json snapshot written on every rebuild for external tooling and debugging
• Configurable WORKFLOWS_DIR, GLOBAL_INSTRUCTIONS_PATH, and debounce interval

Agent-friendly output:

• workflow_get always includes globalInstructions alongside the workflow — no second call needed
• Discriminated source field (permanent | temp) on every workflow_get response
• Typed error contracts with structured reason codes (not_found, version_not_found, already_exists, index_unavailable) so callers can branch on error type rather than parsing messages
• workflow_list with includeTools: true surfaces all MCP server/tool dependencies at a glance

Getting started

No API keys required. The server reads from a local workflows-yaml/ directory by default.

Add the following to your MCP client configuration file:

{
  "mcpServers": {
    "workflows": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/workflows-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "WORKFLOWS_DIR": "/absolute/path/to/your/workflows-yaml"
      }
    }
  }
}

Or with npx (no Bun required):

{
  "mcpServers": {
    "workflows": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@cyanheads/workflows-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "WORKFLOWS_DIR": "/absolute/path/to/your/workflows-yaml"
      }
    }
  }
}

Or with Docker:

{
  "mcpServers": {
    "workflows": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "MCP_TRANSPORT_TYPE=stdio",
        "-v", "/absolute/path/to/your/workflows-yaml:/workflows-yaml",
        "-e", "WORKFLOWS_DIR=/workflows-yaml",
        "ghcr.io/cyanheads/workflows-mcp-server:latest"
      ]
    }
  }
}

For Streamable HTTP, set the transport and start the server:

MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http
# Server listens at http://localhost:3010/mcp

Seed workflows

The repository ships a workflows-yaml/ directory with example workflows organized under categories/. These are ready to use as a starting point. The workflows-yaml/global_instructions.md file contains instructions the server prepends to every workflow_get response — edit it to set global guidance for your agent.

Prerequisites

• Bun v1.3.2 or higher (or Node.js v24+).
• A local directory containing YAML workflow files (or use the bundled workflows-yaml/ seed).

Installation

1. Clone the repository:

git clone https://github.com/cyanheads/workflows-mcp-server.git

1. Navigate into the directory:

cd workflows-mcp-server

1. Install dependencies:

bun install

1. Configure environment:

cp .env.example .env
# edit .env if needed — most settings have defaults

Configuration

See .env.example for the full list of optional overrides.

Running the server

Local development

• Build and run:

  # One-time build
  bun run rebuild
  
  # Run the built server
  bun run start:stdio
  # or
  bun run start:http
  

• Run checks and tests:

  bun run devcheck   # Lint, format, typecheck, security
  bun run test       # Vitest test suite
  bun run lint:mcp   # Validate MCP definitions against spec
  

Docker

docker build -t workflows-mcp-server .
docker run --rm \
  -v /path/to/workflows-yaml:/workflows-yaml \
  -e WORKFLOWS_DIR=/workflows-yaml \
  -p 3010:3010 \
  workflows-mcp-server

The Dockerfile defaults to HTTP transport, stateless session mode, and logs to /var/log/workflows-mcp-server. OpenTelemetry peer dependencies are installed by default — build with --build-arg OTEL_ENABLED=false to omit them.

Project structure

Development guide

See CLAUDE.md for development guidelines and architectural rules. The short version:

• Handlers throw, framework catches — no try/catch in tool logic
• Use ctx.log for request-scoped logging
• Register new tools via the barrel in src/mcp-server/tools/definitions/index.ts
• Filesystem operations go through WorkflowIndexService, not directly in tool handlers

Contributing

Issues and pull requests are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

License

Apache-2.0 — see LICENSE for details.