Files
mcpctl/.taskmaster/tasks/task_109.md
Michal a869f77070 merge: AgentProject membership — the junction is now load-bearing
Merges feat/agent-project-membership (task 166/152). An agent can finally join
many projects: membership routes, per-membership role and optional brain
override, chat resolving context from the membership, and CLI attach-agent /
detach-agent / get memberships. The legacy Agent.projectId fallback is kept for
this release as the schema comment promises.

Conflict resolved in main.ts: that branch added its RBAC case to
mapUrlToPermission inline, while this branch had extracted the function to
middleware/url-permission.ts so it could be tested. Kept the extraction and
ported the case into it — joining a team is `edit:agents:<name>`, not
`create:agents`, which is the authority to mint a whole agent.

Also fixes something the extraction makes possible. security.test.ts contained a
hand-copied reproduction of mapUrlToPermission, because main.ts self-invokes
main() and nothing in it was importable. A security test asserting against a
copy stops testing the system the moment the real one changes, and this copy had
already drifted. It now imports the real function; all 18 assertions still pass,
against the code that actually runs.

Local: build clean, workspace 2550 passed, lint unchanged at 794 errors.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N4wNHWf7xSwnZCWpJcyv9p
2026-08-09 23:34:18 +01:00

2.3 KiB

Task ID: 109

Title: Implement Studio MCP Server Tools

Status: done

Dependencies: 104 ✗, 106 ✓, 107 ✓, 108 ✓

Priority: medium

Description: Create MCP tools for Claude Monitor to observe traffic, get corrections, switch models, and modify stages.

Details:

Extend src/cli/src/commands/console/inspect-mcp.ts with studio tools:

const studioTools: Tool[] = [
  {
    name: 'get_content_diff',
    description: 'Get original vs transformed vs edited content for a specific event',
    inputSchema: {
      type: 'object',
      properties: {
        eventId: { type: 'string', description: 'Event ID' },
      },
      required: ['eventId'],
    },
  },
  {
    name: 'get_corrections',
    description: 'Get all user corrections (edits) in a session',
    inputSchema: {
      type: 'object',
      properties: {
        sessionId: { type: 'string', description: 'Optional session filter' },
      },
    },
  },
  {
    name: 'get_active_model',
    description: 'Get current proxymodel name and stage list for a project',
    inputSchema: {
      type: 'object',
      properties: {
        project: { type: 'string' },
      },
      required: ['project'],
    },
  },
  {
    name: 'switch_model',
    description: 'Hot-swap the active proxymodel on a project',
    inputSchema: {
      type: 'object',
      properties: {
        project: { type: 'string' },
        model: { type: 'string' },
      },
      required: ['project', 'model'],
    },
  },
  {
    name: 'reload_stages',
    description: 'Force reload all stages from ~/.mcpctl/stages/',
    inputSchema: { type: 'object', properties: {} },
  },
  {
    name: 'get_stage_source',
    description: 'Read the source code of a stage file',
    inputSchema: {
      type: 'object',
      properties: {
        name: { type: 'string' },
      },
      required: ['name'],
    },
  },
  {
    name: 'list_models',
    description: 'List available proxymodels',
    inputSchema: { type: 'object', properties: {} },
  },
  {
    name: 'list_stages',
    description: 'List available stages',
    inputSchema: { type: 'object', properties: {} },
  },
];

Test Strategy:

Integration test with MCP client: each tool returns expected data format, switch_model actually changes the model, reload_stages picks up file changes, get_corrections returns user edits.