MCP Integration

The Specor MCP server exposes your product graph as a set of read-only tools that any MCP-compatible AI client can call. This lets Claude Desktop, Cursor, Windsurf, and other clients pull full product context — requirements, flows, rules, acceptance criteria — before writing or reviewing code, without leaving your editor.

What you can do

Once connected, your AI assistant can:

Read the graph — fetch domains, capabilities, features, flows, rules, metrics, and acceptance criteria in any branch
Search and list nodes — full-text search, or list nodes filtered by type
Inspect history — node change history, recent commits, and semantic diffs between commits or branches
Review merges and suggestions — merge request details (conflicts, comments, approvals) and pending AI suggestions
Read comments — see the discussion thread on any node

This is a read-only integration — the server has no tools for creating or editing nodes. To make changes to your product model, use the Specor app or in-app chat.

Setup

1. Get your API token

Go to app.specor.ai → Account → API Tokens → New token. Copy the token — it will not be shown again.

2. Add the server to your MCP client

The Specor MCP server is hosted at https://mcp.specor.ai/mcp and uses the SSE transport — no local installation required.

Claude Desktop

Open ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows) and add:

{
  "mcpServers": {
    "specor": {
      "url": "https://mcp.specor.ai/mcp",
      "headers": {
        "Authorization": "Bearer your-token-here",
        "X-Workspace-ID": "your-workspace-id"
      }
    }
  }
}

Restart Claude Desktop. You should see a Specor tool indicator in the chat input.

Cursor

In Cursor Settings → MCP → Add server:

{
  "specor": {
    "url": "https://mcp.specor.ai/mcp",
    "headers": {
      "Authorization": "Bearer your-token-here",
      "X-Workspace-ID": "your-workspace-id"
    }
  }
}

Other clients

Any client that supports the MCP SSE transport works. Point it at https://mcp.specor.ai/mcp and pass Authorization: Bearer <token> and X-Workspace-ID: <workspace-id> as request headers.

3. Optional: scope to a branch

By default the server reads from your workspace’s main branch. To work on a specific branch, add the X-Branch-ID header (or pass branch_id per tool call):

"headers": {
  "Authorization": "Bearer your-token-here",
  "X-Workspace-ID": "your-workspace-id",
  "X-Branch-ID": "your-branch-id"
}

You can find branch IDs in the Branches view inside the app, or via the list_branches tool.

Available tools

Tool	Description
`get_feature`	Get a feature with its needs, rules, ACs, flows, metrics, personas, and decisions
`list_features`	List features, optionally filtered by capability
`get_capability`	Get a capability with its child features and parent domain chain
`get_domain_overview`	Summary of all domains and capabilities, with graph-level stats
`get_flow_steps`	Get all flows with ordered steps for a feature
`get_rules`	Get all business rules governing a feature
`get_acceptance_criteria`	Get all acceptance criteria for a feature
`search_features`	Full-text search across features, rules, ACs, needs, and other node types
`list_nodes`	List nodes in the graph, optionally filtered by type or keyword
`get_product_context`	Get the richest available context pack for any node, auto-selected by type
`get_node_history`	Get the change history for a specific node
`get_node_comments`	Get the comment thread for a node
`get_ontology`	Get the active product ontology (node types, relation types, cardinality)
`list_branches`	List branches in the workspace
`get_branch`	Get details for a single branch
`get_recent_changes`	Get sealed commits from the last N days with diff summaries
`get_commit`	Get metadata for a specific sealed commit
`get_diff`	Compute the semantic diff between two commits or branches
`list_merge_requests`	List merge requests in the workspace
`get_merge_request`	Get full details for a merge request — conflicts, comments, approvals
`list_suggestions`	List pending AI-generated product consistency suggestions

Example prompts

Once connected, try these in your AI client:

“What features does the Checkout domain have and which ones are missing metrics?”

“What are the business rules and acceptance criteria for the One-click Purchase feature?”

“Show me all pending AI suggestions for the payments branch and explain the naming ones.”

“What changed on main in the last week, and is there an open merge request for the fraud-detection branch?”

Permissions

The MCP server uses your API token and respects your role — any token with workspace access can read. Since the server is read-only, there is no write-permission distinction between Viewer, Editor, and Admin tokens for these tools.

Security

Tokens are scoped to a single workspace
The server is strictly read-only — it cannot modify your product graph
Revoke tokens at any time from Account → API Tokens