# hippo_stuck_candidates_report

Self-improve #3: diagnose the candidate-skill Catch-22.

Agent View of the PolicyLayer registry record for `hippo_stuck_candidates_report`. HTML page: https://policylayer.com/tools/verimem/hippo-stuck-candidates-report

## Facts

- Tool: `hippo_stuck_candidates_report`
- Server: Verimem (`aureliocpr-ctrl/verimem`) — https://policylayer.com/tools/verimem.md
- Homepage: https://github.com/aureliocpr-ctrl/verimem
- 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": "hippo_stuck_candidates_report",
    "arguments": {}
  }
}
```

## Why hippo_stuck_candidates_report is rated Low

This tool retrieves and analyzes information about candidate-skill mismatches for diagnostic purposes. No write operations, destructive actions, code execution, or financial transactions are indicated. The read-only nature of generating a diagnostic report, combined with the broader context of a trusted memory engine, suggests this is a data retrieval and analysis operation with no side effects.

From the tool's own definition: "Tool name contains 'report' and description indicates diagnostic analysis ('diagnose'). The function appears to query or analyze existing candidate-skill data to identify catch-22 patterns, with no indication of modifying, executing external operations,…"

## Use case

AI agents call hippo_stuck_candidates_report to retrieve information from Verimem 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 Verimem:

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

## Other tools on Verimem (236)

- `hippo_fact_forget` — Destructive — https://policylayer.com/tools/verimem/hippo-fact-forget.md
- `hippo_fact_forget_with_undo` — Destructive — https://policylayer.com/tools/verimem/hippo-fact-forget-with-undo.md
- `hippo_forget` — Destructive — https://policylayer.com/tools/verimem/hippo-forget.md
- `hippo_forget_scope` — Destructive — https://policylayer.com/tools/verimem/hippo-forget-scope.md
- `hippo_skill_archive` — Destructive — https://policylayer.com/tools/verimem/hippo-skill-archive.md
- `hippo_skill_retire` — Destructive — https://policylayer.com/tools/verimem/hippo-skill-retire.md
- `hippo_compose_plan` — Execute — https://policylayer.com/tools/verimem/hippo-compose-plan.md
- `hippo_consolidate` — Execute — https://policylayer.com/tools/verimem/hippo-consolidate.md
- `hippo_curate_pipeline` — Execute — https://policylayer.com/tools/verimem/hippo-curate-pipeline.md
- `hippo_decay_run` — Execute — https://policylayer.com/tools/verimem/hippo-decay-run.md
- `hippo_plan_strips` — Execute — https://policylayer.com/tools/verimem/hippo-plan-strips.md
- `hippo_provider_switch` — Execute — https://policylayer.com/tools/verimem/hippo-provider-switch.md
- `hippo_reason` — Execute — https://policylayer.com/tools/verimem/hippo-reason.md
- `hippo_rollout_actions` — Execute — https://policylayer.com/tools/verimem/hippo-rollout-actions.md
- `hippo_run_task` — Execute — https://policylayer.com/tools/verimem/hippo-run-task.md
- `hippo_skill_compile_macro` — Execute — https://policylayer.com/tools/verimem/hippo-skill-compile-macro.md
- `hippo_skill_derive_predicates` — Execute — https://policylayer.com/tools/verimem/hippo-skill-derive-predicates.md
- `hippo_skills_derive_predicates_batch` — Execute — https://policylayer.com/tools/verimem/hippo-skills-derive-predicates-batch.md
- `hippo_world_simulate` — Execute — https://policylayer.com/tools/verimem/hippo-world-simulate.md
- `sandbox_exec` — Execute — https://policylayer.com/tools/verimem/sandbox-exec.md
- `hippo_dream_propose` — Other — https://policylayer.com/tools/verimem/hippo-dream-propose.md
- `hippo_agent_specialization` — Read — https://policylayer.com/tools/verimem/hippo-agent-specialization.md
- `hippo_agent_workload` — Read — https://policylayer.com/tools/verimem/hippo-agent-workload.md
- `hippo_anchor_recall` — Read — https://policylayer.com/tools/verimem/hippo-anchor-recall.md
- `hippo_anti_confab_scan` — Read — https://policylayer.com/tools/verimem/hippo-anti-confab-scan.md
- `hippo_assess_confidence` — Read — https://policylayer.com/tools/verimem/hippo-assess-confidence.md
- `hippo_assess_fact_freshness` — Read — https://policylayer.com/tools/verimem/hippo-assess-fact-freshness.md
- `hippo_audit_summary` — Read — https://policylayer.com/tools/verimem/hippo-audit-summary.md
- `hippo_audit_tail` — Read — https://policylayer.com/tools/verimem/hippo-audit-tail.md
- `hippo_briefing` — Read — https://policylayer.com/tools/verimem/hippo-briefing.md
- …and 206 more: https://policylayer.com/tools/verimem.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=verimem · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/verimem