Tanjiren MCP Server
Integrate your AI tools with Tanjiren.
New to Tanjiren? Start with Core Concepts
Understand workstations, tasks, workers, investigations, runbooks, and organizations.
MCP Server
Tanjiren exposes a remote Model Context Protocol (MCP) server. Any MCP-compatible client can connect to it and interact with your Tanjiren organization — list workstations, create tasks, manage prompts, and more — all from your AI assistant.
AI-readable docs
Tanjiren now also exposes public, agent-friendly documentation so MCP clients and AI systems can discover the platform without scraping the visual UI.
Connect
The only thing you need is the server URL:
https://mcp.tanjiren.app/mcpClaude Code
claude mcp add --transport http tanjiren https://mcp.tanjiren.app/mcpVS Code
Use the MCP: Add Server command or add Tanjiren to .vscode/mcp.json.
Cursor
Open Settings → MCP → Add Server, or add it to .cursor/mcp.json.
ChatGPT
Use Developer mode Apps settings and create an app from the remote MCP URL.
Other MCP clients
Add the URL as a Streamable HTTP remote server. Tanjiren follows the MCP specification — any compliant client will work.
Your client will open a browser window for you to sign in with your Tanjiren account. After authorization, you're connected — no API keys or manual configuration needed.
For exact client-specific setup, see Connect MCP clients.
Authentication
Tanjiren uses OAuth 2.1 with PKCE. The flow is fully automatic:
- Your MCP client discovers the OAuth server via
.well-known/oauth-protected-resource - It registers itself via Dynamic Client Registration (RFC 7591)
- A browser window opens for you to sign in with your Tanjiren account
- The client receives a scoped access token — no secrets to manage
Available tools
The tools available to you depend on your organization role:
| Tool | Description | Scope |
|---|---|---|
| whoami | Your identity, organization, and role | mcp:read |
| list_workstations | All workstations in your organization | mcp:read |
| get_workstation | Details and status of a specific workstation | mcp:read |
| list_workers | Workers with health, capacity, and routing state | mcp:read |
| get_worker | Details of a specific worker | mcp:read |
| list_runbooks | Reusable task blueprints | mcp:read |
| get_runbook | Details of a specific runbook | mcp:read |
| list_investigations | Investigations and grouped analysis work | mcp:read |
| get_investigation | Details of a specific investigation | mcp:read |
| list_prompts | Saved prompts in your organization | mcp:read |
| list_tasks | Recent tasks and their execution state | mcp:read |
| get_task | Details of a specific task | mcp:read |
| list_org_members | Members of your organization | mcp:read |
| list_audit_events | Audit log (admin only) | mcp:governance:read |
| create_task | Delegate a prompt or command to workstations | mcp:operate |
| cancel_task | Cancel a running or pending task | mcp:operate |
| create_investigation | Create a new investigation container | mcp:operate |
| add_task_artifact | Attach durable evidence or notes to a task | mcp:operate |
| approve_task | Approve a pending task | mcp:operate |
| reject_task | Reject a pending task | mcp:operate |
| retry_task | Retry a failed or cancelled task | mcp:operate |
| create_prompt | Save a new prompt | mcp:operate |
Available resources
In addition to tools, Tanjiren exposes read-only MCP resources for stable context that hosts can cache, inspect, and hand to the model without treating every read as an action.
| Resource | Type | Description |
|---|---|---|
| tanjiren://session/whoami | static | Current user, org, plan, and granted scopes. |
| tanjiren://org/current | static | Current organization summary and available capabilities. |
| tanjiren://limits/current | static | Plan-derived limits and capability flags (canOperate, canReadGovernance). |
| tanjiren://org/current/security-policy | static | Trusted-controller policy summary affecting task execution, relay, and rotation. |
| tanjiren://org/current/doctrine | static | Organization doctrine and operational guidance. |
| tanjiren://docs/mcp-overview | static | Canonical MCP usage guidance for an AI client. |
| tanjiren://tasks/runtime-overview | static | Organization-wide task runtime summary. |
| tanjiren://workers/runtime-overview | static | Organization-wide worker health and routing summary. |
| tanjiren://workstations/{instanceId} | template | Canonical workstation record for one workstation. |
| tanjiren://tasks/{taskId} | template | Canonical task record with execution, steps, and artifacts. |
| tanjiren://workers/{workerId} | template | Canonical worker record for one worker. |
Workflow prompts
Tanjiren MCP exposes workflow prompts — reusable templates that teach an AI client how to use the surface safely. Prompts do not mutate state; they return structured guidance.
| Prompt | Description |
|---|---|
| start_here | Bootstrap a session with identity, scope, plan, and constraints. |
| diagnose_workstation | Investigate one workstation using a read-first workflow. |
| investigate_task_execution | Review a task execution with step-level analysis. |
| prepare_safe_task | Plan a task before executing it. Validates scope, plan, targets, and policy. |
| summarize_org_activity | Produce a concise operational summary. |
Scopes and permissions
Access is granted based on your organization role. Your MCP client may request scopes, but the server clamps them to what your role allows:
| Role | mcp:read | mcp:operate | mcp:governance:read |
|---|---|---|---|
| Viewer | Yes | — | — |
| Member | Yes | Yes | — |
| Admin | Yes | Yes | Yes |
| Owner | Yes | Yes | Yes |
Example usage
Once connected, just ask your AI assistant naturally: