Granoflow MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GRANOFLOW_API_TOKEN | No | API token for authenticating with the Granoflow API. | |
| GRANOFLOW_API_BASE_URL | No | The base URL of the Granoflow Local HTTP API. Default: http://127.0.0.1:56789 | http://127.0.0.1:56789 |
| GRANOFLOW_MCP_CONFIG_PATH | No | Path to a custom config file. Default: ~/.config/granoflow-mcp/config.json |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| granoflow_setup_statusA | Inspect Granoflow MCP config and Local HTTP API health without printing secrets. |
| granoflow_setup_detect_local_apiA | Probe a bounded localhost port list for a running Granoflow Local HTTP API. |
| granoflow_setup_write_configC | Preview or write MCP-owned non-secret Granoflow connection config. Defaults to dry-run. |
| granoflow_setup_open_configB | Create and optionally open the MCP-owned non-secret Granoflow config file. |
| granoflow_setup_open_appB | Preview or open the installed Granoflow app after user approval. Defaults to dry-run. |
| granoflow_healthA | Check whether the Granoflow Local HTTP API is reachable. |
| granoflow_versionA | Show Granoflow app and Local HTTP API version metadata. |
| granoflow_capabilitiesA | List capabilities exposed by the running Granoflow app. |
| granoflow_ai_agent_toolsB | List Granoflow AI-agent tool contracts. |
| granoflow_task_listC | List tasks from Granoflow. |
| granoflow_task_exportC | Export a task context for an AI agent. |
| granoflow_task_validateB | Validate an AI-agent task result before importing it into Granoflow. |
| granoflow_task_importA | Import an AI-agent task result into Granoflow. Use dryRun first unless the user explicitly asks to write. |
| granoflow_task_createC | Create a Granoflow task from a JSON payload. |
| granoflow_task_updateB | Update a Granoflow task through the Local HTTP API. |
| granoflow_task_completeC | Complete a Granoflow task. |
| granoflow_project_listA | List Granoflow projects. |
| granoflow_review_day_showC | Show a Granoflow daily review by date. |
| granoflow_api_requestB | Run an allowed Granoflow Local HTTP API request. Prefer dedicated tools when available. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 19 tools
Most tools have clearly distinct purposes (task CRUD, setup, project list, review show, health, version). The granoflow_api_request is a generic fallback that could overlap, but its description advises preferring dedicated tools.
All tools use a consistent snake_case pattern with the 'granoflow_' prefix. The naming follows a verb_noun or noun_verb structure, though some tools like 'granoflow_health' use a single noun. No mixed conventions observed.
19 tools is slightly above the typical 3-15 well-scoped range, but given the breadth of functionality (setup, task management, AI integration, project listing, etc.), the count is still reasonable and not excessive.
The task surface is decent (create, list, update, complete, export, import, validate) but lacks a delete task operation. Project management is limited to listing; no create/update/delete for projects or reviews. Notable gaps exist.