# semantic_search

A read tool on the Metis Public Health MCP server.

Agent View of the PolicyLayer registry record for `semantic_search`. HTML page: https://policylayer.com/tools/sveritg-metis-ph/semantic-search

## Facts

- Tool: `semantic_search`
- Server: Metis Public Health (`sveritg/metis_ph`) — https://policylayer.com/tools/sveritg-metis-ph.md
- Homepage: https://github.com/SVerITG/Metis_PH
- 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": "semantic_search",
    "arguments": {}
  }
}
```

## Why semantic_search is rated Low

Semantic search retrieves and queries data from an indexed knowledge base without creating, modifying, deleting, executing code, or moving funds. The operation is read-only with no side effects. Severity is low because the tool only exposes information already in the user's own local library, with no capability to alter state or execute operations.

From the tool's own definition: "Tool name is 'semantic_search' which, by standard terminology in information retrieval and library systems, performs a search operation."

## Use case

AI agents call semantic_search to retrieve information from Metis Public Health 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 Metis Public Health:

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

## Other tools on Metis Public Health (276)

- `archive_library_item` — Destructive — https://policylayer.com/tools/sveritg-metis-ph/archive-library-item.md
- `delete_data_trigger` — Destructive — https://policylayer.com/tools/sveritg-metis-ph/delete-data-trigger.md
- `delete_knowledge_database` — Destructive — https://policylayer.com/tools/sveritg-metis-ph/delete-knowledge-database.md
- `delete_task` — Destructive — https://policylayer.com/tools/sveritg-metis-ph/delete-task.md
- `remove_first_run_marker` — Destructive — https://policylayer.com/tools/sveritg-metis-ph/remove-first-run-marker.md
- `remove_library_item` — Destructive — https://policylayer.com/tools/sveritg-metis-ph/remove-library-item.md
- `remove_project` — Destructive — https://policylayer.com/tools/sveritg-metis-ph/remove-project.md
- `remove_tracked_file` — Destructive — https://policylayer.com/tools/sveritg-metis-ph/remove-tracked-file.md
- `reset_thinking_profile` — Destructive — https://policylayer.com/tools/sveritg-metis-ph/reset-thinking-profile.md
- `analyze_script` — Execute — https://policylayer.com/tools/sveritg-metis-ph/analyze-script.md
- `dhis2_query` — Execute — https://policylayer.com/tools/sveritg-metis-ph/dhis2-query.md
- `generate_profiling_script` — Execute — https://policylayer.com/tools/sveritg-metis-ph/generate-profiling-script.md
- `install_background_pack` — Execute — https://policylayer.com/tools/sveritg-metis-ph/install-background-pack.md
- `run_maintenance` — Execute — https://policylayer.com/tools/sveritg-metis-ph/run-maintenance.md
- `run_metis` — Execute — https://policylayer.com/tools/sveritg-metis-ph/run-metis.md
- `run_trigger_now` — Execute — https://policylayer.com/tools/sveritg-metis-ph/run-trigger-now.md
- `scaffold_script` — Execute — https://policylayer.com/tools/sveritg-metis-ph/scaffold-script.md
- `scan_project_scripts` — Execute — https://policylayer.com/tools/sveritg-metis-ph/scan-project-scripts.md
- `start_course_build` — Execute — https://policylayer.com/tools/sveritg-metis-ph/start-course-build.md
- `start_interest_interview` — Execute — https://policylayer.com/tools/sveritg-metis-ph/start-interest-interview.md
- `brainstorm_turn` — Other — https://policylayer.com/tools/sveritg-metis-ph/brainstorm-turn.md
- `end_span` — Other — https://policylayer.com/tools/sveritg-metis-ph/end-span.md
- `start_span` — Other — https://policylayer.com/tools/sveritg-metis-ph/start-span.md
- `aggregate_reflexions` — Read — https://policylayer.com/tools/sveritg-metis-ph/aggregate-reflexions.md
- `anonymize_text` — Read — https://policylayer.com/tools/sveritg-metis-ph/anonymize-text.md
- `ask_library` — Read — https://policylayer.com/tools/sveritg-metis-ph/ask-library.md
- `assemble_brainstorm_context` — Read — https://policylayer.com/tools/sveritg-metis-ph/assemble-brainstorm-context.md
- `audit_background_provenance` — Read — https://policylayer.com/tools/sveritg-metis-ph/audit-background-provenance.md
- `backup_db` — Read — https://policylayer.com/tools/sveritg-metis-ph/backup-db.md
- `check_data_safety` — Read — https://policylayer.com/tools/sveritg-metis-ph/check-data-safety.md
- …and 246 more: https://policylayer.com/tools/sveritg-metis-ph.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=sveritg-metis-ph · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/sveritg-metis-ph