Granoflow MCP server

Update a Granoflow task with common structured fields. Defaults to dry-run.

List Granoflow projects.

Update a Granoflow project with common structured fields. Defaults to dry-run.

Safely delete a Granoflow project. Defaults to dry-run and requires confirmTitle for writes.

Create a Granoflow milestone with common structured fields. Defaults to dry-run.

Safely delete a Granoflow milestone. Defaults to dry-run and requires confirmTitle for writes.

Run an allowed Granoflow Local HTTP API request. Prefer dedicated tools when available.

Probe a bounded localhost port list for a running Granoflow Local HTTP API.

Preview or open the installed Granoflow app after user approval. Defaults to dry-run.

Show Granoflow app and Local HTTP API version metadata.

List Granoflow AI-agent tool contracts from the running app. Use with granoflow_agent_workflow_skill for task, review, and memory-style questions.

Export task details, completion review, project context, and reusable lessons for evidence-based task or memory retrieval.

Import an AI-agent task result into Granoflow. Use dryRun first unless the user explicitly asks to write.

Create a Granoflow task with common structured fields. Defaults to dry-run.

Preview or write MCP-owned non-secret Granoflow connection config. Defaults to dry-run.

Inspect Granoflow MCP config and Local HTTP API health without printing secrets.

List capabilities exposed by the running Granoflow app.

List tasks from Granoflow.

Validate an AI-agent task result before importing it into Granoflow.

Create a Granoflow task from a JSON payload.

Update a Granoflow task through the Local HTTP API.

Low-level compatibility endpoint to complete a Granoflow task. Prefer granoflow_task_finish for any user-facing completion request so startedAt, endedAt, review, and review cards can be captured.

Resolve Granoflow task candidates by title without creating or updating data.

Read the bundled Granoflow Agent Workflow skill. Call this when a user works with Granoflow tasks, finishes tasks, asks for daily, weekly, or monthly reviews, mood or efficiency review notes, task reviews, review cards, historical context, decisions, lessons, similar past work, or long-term work memory, or politely/strongly signals that Granoflow/MCP/generated agent output is wrong or misaligned. Do not call it for unrelated venting or unrelated disagreement.

Create and optionally open the MCP-owned non-secret Granoflow config file.

Create a Granoflow project with common structured fields. Defaults to dry-run.

Resolve Granoflow milestone candidates by title without creating or updating data.

Show a Granoflow daily review by date.

Finish a Granoflow task from the current agent conversation: infer startedAt and endedAt, write only meaningful review content, create one review card per durable knowledge point, complete the task, and verify status=done.

Resolve Granoflow project candidates by title without creating or updating data.

List Granoflow milestones.

Update a Granoflow milestone with common structured fields. Defaults to dry-run.

Check whether the Granoflow Local HTTP API is reachable.