# agent_search

A read tool on the C4REQBER MCP server.

Agent View of the PolicyLayer registry record for `agent_search`. HTML page: https://policylayer.com/tools/c4reqber/agent-search

## Facts

- Tool: `agent_search`
- Server: C4REQBER (`C4MIND/C4REQBER`) — https://policylayer.com/tools/c4reqber.md
- Homepage: https://github.com/C4MIND/C4REQBER
- 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": "agent_search",
    "arguments": {}
  }
}
```

## Why agent_search is rated Low

The tool name and server context indicate a search function that retrieves or queries data without modifying state. However, confidence is moderate (0.6) because the description is empty, leaving ambiguity about actual implementation and parameters. A read-only server context supports the Read classification, but thorough verification of the tool's actual behavior would improve confidence.

From the tool's own definition: "Tool name 'agent_search' suggests a query/search operation typical of Read category. Server description emphasizes 'read-only mirror' and 'discovery pipeline', consistent with retrieval without side effects."

## Use case

AI agents call agent_search to retrieve information from C4REQBER 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 C4REQBER:

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

## Other tools on C4REQBER (31)

- `c4_agent_query` — Execute — https://policylayer.com/tools/c4reqber/c4-agent-query.md
- `c4_agent_solve` — Execute — https://policylayer.com/tools/c4reqber/c4-agent-solve.md
- `c4_agent_spawn` — Execute — https://policylayer.com/tools/c4reqber/c4-agent-spawn.md
- `c4_agent_turbo` — Execute — https://policylayer.com/tools/c4reqber/c4-agent-turbo.md
- `c4_codegen` — Execute — https://policylayer.com/tools/c4reqber/c4-codegen.md
- `blast_auto` — Other — https://policylayer.com/tools/c4reqber/blast-auto.md
- `blast_flash` — Other — https://policylayer.com/tools/c4reqber/blast-flash.md
- `blast_turbo` — Other — https://policylayer.com/tools/c4reqber/blast-turbo.md
- `blast_turbofactory` — Other — https://policylayer.com/tools/c4reqber/blast-turbofactory.md
- `c4_bayesian` — Other — https://policylayer.com/tools/c4reqber/c4-bayesian.md
- `c4_causal` — Other — https://policylayer.com/tools/c4reqber/c4-causal.md
- `c4_meta` — Other — https://policylayer.com/tools/c4reqber/c4-meta.md
- `c4_social` — Other — https://policylayer.com/tools/c4reqber/c4-social.md
- `c4_transfer` — Other — https://policylayer.com/tools/c4reqber/c4-transfer.md
- `c4_triz` — Other — https://policylayer.com/tools/c4reqber/c4-triz.md
- `agent_fingerprint` — Read — https://policylayer.com/tools/c4reqber/agent-fingerprint.md
- `agent_process` — Read — https://policylayer.com/tools/c4reqber/agent-process.md
- `agent_solve` — Read — https://policylayer.com/tools/c4reqber/agent-solve.md
- `blast_solve` — Read — https://policylayer.com/tools/c4reqber/blast-solve.md
- `c4_agent_poll` — Read — https://policylayer.com/tools/c4reqber/c4-agent-poll.md
- `c4_agent_skills` — Read — https://policylayer.com/tools/c4reqber/c4-agent-skills.md
- `c4_agent_soul` — Read — https://policylayer.com/tools/c4reqber/c4-agent-soul.md
- `c4_autoresearch` — Read — https://policylayer.com/tools/c4reqber/c4-autoresearch.md
- `c4_chain` — Read — https://policylayer.com/tools/c4reqber/c4-chain.md
- `c4_fingerprint` — Read — https://policylayer.com/tools/c4reqber/c4-fingerprint.md
- `c4_prove` — Read — https://policylayer.com/tools/c4reqber/c4-prove.md
- `c4_search` — Read — https://policylayer.com/tools/c4reqber/c4-search.md
- `c4_simulate` — Read — https://policylayer.com/tools/c4reqber/c4-simulate.md
- `c4_solve` — Read — https://policylayer.com/tools/c4reqber/c4-solve.md
- `c4_verify` — Read — https://policylayer.com/tools/c4reqber/c4-verify.md
- …and 1 more: https://policylayer.com/tools/c4reqber.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=c4reqber · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/c4reqber