# mmp_search

Search index metadata; returns candidates without body text.

Agent View of the PolicyLayer registry record for `mmp_search`. HTML page: https://policylayer.com/tools/dense-knowledge-mcp/mmp-search

## Facts

- Tool: `mmp_search`
- Server: Pypi:dense Knowledge (`Lucky44k/dense-knowledge-mcp`) — https://policylayer.com/tools/dense-knowledge-mcp.md
- Homepage: https://github.com/Lucky44k/dense-knowledge-mcp
- Risk category: Read (Low risk)
- Registry record: grade B, 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": "mmp_search",
    "arguments": {}
  }
}
```

## Why mmp_search is rated Low

The mmp_search tool performs a read-only query of metadata in a knowledge storage system. It searches an index and returns candidates, with no indication of side effects, data modification, or irreversible actions. The explicit note that it 'returns candidates without body text' further confirms it is a retrieval operation.

From the tool's own definition: "Tool description states 'Search index metadata; returns candidates without body text.' This is a retrieval operation that queries an index and returns results without modifying data."

## Use case

AI agents call mmp_search to retrieve information from Pypi:dense Knowledge 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 Pypi:dense Knowledge:

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

## Other tools on Pypi:dense Knowledge (7)

- `mmp_deprecate` — Read — https://policylayer.com/tools/dense-knowledge-mcp/mmp-deprecate.md
- `mmp_list` — Read — https://policylayer.com/tools/dense-knowledge-mcp/mmp-list.md
- `mmp_open` — Read — https://policylayer.com/tools/dense-knowledge-mcp/mmp-open.md
- `mmp_read` — Read — https://policylayer.com/tools/dense-knowledge-mcp/mmp-read.md
- `mmp_validate` — Read — https://policylayer.com/tools/dense-knowledge-mcp/mmp-validate.md
- `mmp_create` — Write — https://policylayer.com/tools/dense-knowledge-mcp/mmp-create.md
- `mmp_update` — Write — https://policylayer.com/tools/dense-knowledge-mcp/mmp-update.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=dense-knowledge-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/dense-knowledge-mcp