Workflows Server

---

Overview

A declarative workflow library for LLM agents, backed by local YAML files. Store, list, and retrieve named, versioned multi-step playbooks — each a sequence of MCP server/tool calls — for permanent reuse or one-shot temporary runs. Runs as a stdio process or a local Streamable HTTP server; an in-memory index rebuilds automatically as files change.

Tools

Tool	Description
workflow_list	List all permanent workflows in the index, with optional keyword, category, and tag filters.
workflow_get	Retrieve a complete workflow definition by name, with global instructions prepended.
workflow_create	Write a new permanent workflow YAML to the library.
workflow_create_temp	Write a temporary one-shot workflow, indexed but excluded from list results.
workflow_delete	Permanently remove a permanent workflow by name and optional version.

Capability reference

workflow_list _tool

• Optional keyword query filter (case-insensitive substring across workflow name and description)
• 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
• Empty results echo the applied filters with a hint to broaden

---

workflow_get _tool

• 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 _tool

• Workflow stored at categories/<slugified-category>/<slugified-name>-<slugified-version>-workflow.yaml — one file per name@version, so multiple versions coexist
• 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 _tool

• 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

---

workflow_delete _tool

• Semver-aware: omit version to delete the highest available match; specify a version to target one exactly
• Only permanent workflows can be deleted — temporary workflows are rejected (they expire on their own)
• Irreversible: the file is removed and the workflow no longer appears in workflow_list or workflow_get

Features

Built on @cyanheads/mcp-ts-core: stdio and Streamable HTTP transports, pluggable auth (none / jwt / oauth), swappable storage (in-memory, filesystem, Supabase, Cloudflare KV/R2/D1), structured logging with optional OpenTelemetry tracing.

Workflow library:

• YAML workflow files validated against a schema at index time; invalid files are skipped and logged, never crash the server
• In-memory index keyed by name@version, built at startup from workflows-yaml/categories/ recursively, kept fresh by a debounced recursive filesystem watcher on any add/change/remove
• Semver-aware lookup — latest version returned when version is omitted
• _index.json snapshot written on every rebuild for external tooling and debugging
• Configurable WORKFLOWS_DIR, GLOBAL_INSTRUCTIONS_PATH, and debounce interval

Agent-friendly output:

• Discriminated output — source: "permanent" | "temp" on every workflow_get response and typed reason codes (not_found, version_not_found, already_exists, temp_not_allowed, index_unavailable, …) on failures, so callers branch on data instead of parsing error strings
• No extra round trip — workflow_get always returns globalInstructions alongside the workflow definition in the same response
• Response shaping — workflow_list's optional includeTools flag pre-derives the unique server/tool pairs used by a workflow, and an empty result echoes the applied filters with a broadening hint instead of returning nothing

---

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-mcp-server": {
      "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-mcp-server": {
      "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-mcp-server": {
      "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 v1.4.0 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

2. Navigate into the directory:

cd workflows-mcp-server

3. Install dependencies:

bun install

4. Configure environment:

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

---

Configuration

Variable	Description	Default
WORKFLOWS_DIR	Absolute or relative path to the workflows root directory.	./workflows-yaml
GLOBAL_INSTRUCTIONS_PATH	Path to the global instructions markdown file. Derives from WORKFLOWS_DIR when not set.	<WORKFLOWS_DIR>/global_instructions.md
WATCHER_DEBOUNCE_MS	Milliseconds to debounce filesystem change events before rebuilding the index.	500
MCP_TRANSPORT_TYPE	Transport: stdio or http.	stdio
MCP_HTTP_PORT	Port for HTTP server.	3010
MCP_SESSION_MODE	HTTP sessions: auto, stateful, or stateless. This server needs no caller-input round trips; setting the variable overrides the declared posture.	stateless, declared in src/index.ts
MCP_AUTH_MODE	Auth mode: none, jwt, or oauth.	none
MCP_LOG_LEVEL	Log level (RFC 5424).	info
OTEL_ENABLED	Enable OpenTelemetry instrumentation (spans, metrics, completion logs).	false

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

Directory	Purpose
src/index.ts	createApp() entry point — registers tools and inits the workflow index service.
src/config/	Server-specific environment variable parsing and validation with Zod.
src/mcp-server/tools/	Tool definitions (*.tool.ts).
src/services/workflow-index/	WorkflowIndexService — YAML parsing, index build, watcher, semver lookup, write helpers.
tests/	Unit and integration tests mirroring src/.
workflows-yaml/	Seed workflow library — categories/ for permanent workflows, temp/ for throwaway ones, global_instructions.md for agent-global guidance.

---

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 are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

---

License

Apache-2.0 — see LICENSE for details.