# get_agent_capability_supply_demand

Analyze supply vs demand for each capability. Supply = agents declaring the capability; demand = active tasks requiring it. Identifies bottleneck (demand exceeds supply), missing (demand, no supply), surplus, and balanced capabilities so owners can rebalance the fleet skills against task requirements.

Agent View of the PolicyLayer registry record for `get_agent_capability_supply_demand`. HTML page: https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/get-agent-capability-supply-demand

## Facts

- Tool: `get_agent_capability_supply_demand`
- Server: Todo for AI MCP Server (`todo-for-ai/todo-for-ai-mcp`) — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp.md
- Homepage: https://github.com/todo-for-ai/todo-for-ai-mcp
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_agent_capability_supply_demand",
    "arguments": {}
  }
}
```

## Why get_agent_capability_supply_demand is rated Low

Even though get_agent_capability_supply_demand only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

## Use case

AI agents call get_agent_capability_supply_demand to retrieve information from Todo for AI MCP Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Todo for AI MCP Server:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_agent_capability_supply_demand": {}
  }
}
```

## Other tools on Todo for AI MCP Server (243)

- `cancel_workflow_run` — Destructive — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/cancel-workflow-run.md
- `clear_step_runtime_override` — Destructive — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/clear-step-runtime-override.md
- `delete_agent_experience` — Destructive — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/delete-agent-experience.md
- `delete_collaboration_template` — Destructive — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/delete-collaboration-template.md
- `delete_knowledge_entry` — Destructive — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/delete-knowledge-entry.md
- `delete_sandbox` — Destructive — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/delete-sandbox.md
- `delete_shared_context` — Destructive — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/delete-shared-context.md
- `delete_workflow` — Destructive — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/delete-workflow.md
- `delete_workflow_trigger` — Destructive — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/delete-workflow-trigger.md
- `revoke_cross_project_agent` — Destructive — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/revoke-cross-project-agent.md
- `revoke_sandbox_execution` — Destructive — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/revoke-sandbox-execution.md
- `append_run_logs` — Execute — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/append-run-logs.md
- `escalate_overdue_tasks` — Execute — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/escalate-overdue-tasks.md
- `handoff_task` — Execute — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/handoff-task.md
- `launch_workflow` — Execute — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/launch-workflow.md
- `pause_workflow_run` — Execute — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/pause-workflow-run.md
- `retry_workflow_run` — Execute — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/retry-workflow-run.md
- `start_sandbox_execution` — Execute — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/start-sandbox-execution.md
- `acknowledge_conflict` — Read — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/acknowledge-conflict.md
- `authorize_cross_project_agent` — Read — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/authorize-cross-project-agent.md
- `auto_extract_experiences` — Read — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/auto-extract-experiences.md
- `auto_extract_knowledge` — Read — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/auto-extract-knowledge.md
- `bind_agent_sandbox` — Read — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/bind-agent-sandbox.md
- `check_sandbox_action` — Read — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/check-sandbox-action.md
- `claim_agent_task` — Read — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/claim-agent-task.md
- `claim_cross_project_task` — Read — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/claim-cross-project-task.md
- `collaboration_graph` — Read — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/collaboration-graph.md
- `collaboration_metrics` — Read — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/collaboration-metrics.md
- `decay_all_experiences` — Read — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/decay-all-experiences.md
- `diff_workflow_versions` — Read — https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp/diff-workflow-versions.md
- …and 213 more: https://policylayer.com/tools/todo-for-ai-todo-for-ai-mcp.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=todo-for-ai-todo-for-ai-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/todo-for-ai-todo-for-ai-mcp