aiproject-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@aiproject-mcp list all my projects"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
AIProject MCP Server
This MCP server wraps the AIProject project/task API described in api.md.
Run
npm install
npm run build
npm startUse aiproject-mcp as a stdio MCP server after build.
Related MCP server: Context Apps
MCP Config
Local build:
{
"mcpServers": {
"aiproject": {
"command": "C:\\ServBay\\bin\\node.cmd",
"args": [
"C:\\Users\\Onur\\Desktop\\mcp\\dist\\src\\index.js"
],
"env": {
"AIPROJECT_BASE_URL": "http://127.0.0.1:8000/",
"AIPROJECT_API_KEY": "<API_KEY>"
}
}
}
}After npm publish:
{
"mcpServers": {
"aiproject": {
"command": "npx",
"args": [
"-y",
"aiproject-mcp"
],
"env": {
"AIPROJECT_BASE_URL": "http://127.0.0.1:8000/",
"AIPROJECT_API_KEY": "<API_KEY>"
}
}
}
}Credentials
The server reads credentials from environment variables:
AIPROJECT_BASE_URL: API root or app root. Bothhttp://127.0.0.1:8000andhttp://127.0.0.1:8000/api/v1are accepted. If the app root is supplied,/api/v1is appended automatically.AIPROJECT_API_KEY: API key sent asX-API-Key.
Every MCP tool also accepts optional credential overrides in its input:
baseUrl: OverrideAIPROJECT_BASE_URLfor one call.apiKey: OverrideAIPROJECT_API_KEYfor one call.
Tools
aiproject_get_me:GET /me; verify the API key and return the current user.aiproject_list_projects:GET /projects; paginated project summaries.aiproject_create_project:POST /projects; create a project withname,github_url,clickup_url.aiproject_get_project:GET /projects/{project}; get one project.aiproject_update_project:PUT /projects/{project}; full project update, all project fields required.aiproject_delete_project:DELETE /projects/{project}; deletes the project and its tasks.aiproject_list_tasks:GET /projects/{project}/tasks; paginated task summaries. Does not returncontent.aiproject_create_task:POST /projects/{project}/tasks; create a task with longcontentand assignments. Returns summary withoutcontent.aiproject_get_task:GET /projects/{project}/tasks/{task}; the only task read tool that returns longcontent.aiproject_update_task:PUT /projects/{project}/tasks/{task}; full task update. The sent assignments replace the old list. Returns summary withoutcontent.aiproject_delete_task:DELETE /projects/{project}/tasks/{task}; deletes the task and assignments.aiproject_update_assignment_status:PATCH /projects/{project}/tasks/{task}/assignments/{type}; update one existing team status. It does not create missing assignments.
Usage Guidance
List tasks first with aiproject_list_tasks because it returns lightweight summaries. Call aiproject_get_task only for the specific task whose long content must be read.
Use aiproject_update_assignment_status when only one team's status changes. Use aiproject_update_task when the title, content, or assignment team list changes.
Test
npm testBy default, the integration test calls http://127.0.0.1:8000/api/v1/me through MCP with a dummy API key and expects the documented 401 auth response. To test with a real key:
$env:AIPROJECT_BASE_URL = "http://127.0.0.1:8000/"
$env:AIPROJECT_API_KEY = "<API_KEY>"
npm testAvailable Tools
12 toolsaiproject_create_projectCreate ProjectC
Calls POST /projects to create a project. Required fields are name, github_url, and clickup_url.
Inputs: name (required), github_url (required), clickup_url (required), baseUrl, +1 more.
aiproject_create_taskCreate Project TaskA
Calls POST /projects/{project}/tasks to create a task with full content and one or more assignments. The API response is a task summary and intentionally omits content.
Inputs: project (required), title (required), content (required), assignments (required), +2 more.
aiproject_delete_projectDelete ProjectADestructive
Calls DELETE /projects/{project}. This also deletes the project's tasks and task assignments. Use only when the user explicitly wants project deletion.
Inputs: project (required), baseUrl, apiKey.
aiproject_delete_taskDelete Project TaskADestructive
Calls DELETE /projects/{project}/tasks/{task}. This also deletes the task's assignment records. Use only when the user explicitly wants task deletion.
Inputs: project (required), task (required), baseUrl, apiKey.
aiproject_get_meGet Current API UserARead-onlyIdempotent
Calls GET /me to verify the supplied apiKey and return the user it belongs to. Use this first when checking credentials or identifying the current API user.
Inputs: baseUrl, apiKey.
aiproject_get_projectGet ProjectARead-onlyIdempotent
Calls GET /projects/{project}. Use this when a single project's metadata is needed.
Inputs: project (required), baseUrl, apiKey.
aiproject_get_taskGet Task DetailARead-onlyIdempotent
Calls GET /projects/{project}/tasks/{task}. This is the only task read endpoint that returns the long content field. Use it only after selecting a specific task from a summary list.
Inputs: project (required), task (required), baseUrl, apiKey.
aiproject_list_projectsList ProjectsARead-onlyIdempotent
Calls GET /projects and returns a paginated lightweight project list with tasks_count. Use this before selecting a project ID for task operations.
Inputs: baseUrl, apiKey, page, per_page.
aiproject_list_tasksList Project TasksARead-onlyIdempotent
Calls GET /projects/{project}/tasks and returns paginated task summaries only. It never returns long content. Use this to scan tasks and optionally filter by assignment type/status before calling aiproject_get_task for one selected task.
Inputs: project (required), baseUrl, apiKey, page, +3 more.
aiproject_update_assignment_statusUpdate Task Assignment StatusA
Calls PATCH /projects/{project}/tasks/{task}/assignments/{type} to update one existing team's status. It does not create a missing assignment; if the task does not already have that type, the API returns 404. Use PUT aiproject_update_task to add or remove teams. The response is a task summary without content.
Inputs: project (required), task (required), type (required), status (required), +2 more.
aiproject_update_projectUpdate ProjectA
Calls PUT /projects/{project}. This is a full project update, so send name, github_url, and clickup_url together.
Inputs: project (required), name (required), github_url (required), clickup_url (required), +2 more.
aiproject_update_taskUpdate Project TaskA
Calls PUT /projects/{project}/tasks/{task}. This is a full task update: title, content, and the complete new assignments list must be sent. Assignments omitted from the list are removed by the API. The response is a task summary without content.
Inputs: project (required), task (required), title (required), content (required), +3 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 12 tools
Each tool targets a distinct operation on projects, tasks, or user info, with clear separation of concerns. No two tools have overlapping purposes.
All tools follow the consistent verb_noun pattern with snake_case, prefixed by 'aiproject_', making the naming predictable and easy to parse.
12 tools is an appropriate scope for a project/task management server, covering CRUD for two main entities plus user and assignment status operations.
Core CRUD lifecycle for projects and tasks is complete. Minor gap: no dedicated assignment creation tool, but assignments are managed through task creation/update, so it's a minor weakness.
Related MCP Connectors
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
Project management MCP for AI agents with safe task reads and writes.
MCP server for generating rough-draft project plans from natural-language prompts.
Related MCP Servers
- AlicenseBqualityDmaintenanceA Model Context Protocol server providing AI assistants with comprehensive project, task, and subtask management capabilities with project-specific storage.2944 npm88MIT
- FlicenseNot gradedqualityDmaintenanceThis MCP server provides an AI-powered productivity suite that connects Todo, Idea, Journal, and Timer apps with AI7-
- FlicenseNot gradedqualityDmaintenanceMCP server integrating with PocketBase to manage tasks and projects. Enables AI models to create tasks, list tasks with status filters, and browse projects.-
- AlicenseCqualityDmaintenanceMCP server for Plane integration, enabling AI agents to interact with Plane APIs and services for project management tasks.100MIT