# search_outputs

[SUPPORT] a0e9133e — READ-ONLY full-text search over a run's OUTPUTS tree (numeric/tabular/array artifacts), backed by DuckDB native FTS (Okapi BM25). Walks outputs_dir recursively and builds a persistent index: each .csv/.json contributes its extracted TEXT content plus a cheap fingerprint (CSV column names / JSON top-level keys / an inferred generating_script); each .npy contributes METADATA ONLY (never array content); images/other binaries contribute filesystem metadata + name only. The multi-word query is scored with BM25 and ranked hits are returned. Canonical-vs-archival is handled TWO-STAGE and is NEVER destructive: a filename heuristic (_old / _old_N / leading underscore) flags a CANDIDATE, and a SHA-256 content hash CONFIRMS — an archival copy byte-identical to its canonical twin is DEPRIORITIZED in ranking (is_archival=true, canonical_path set), while a same-name-pattern file whose content DIFFERS is surfaced as its own distinct hit (never collapsed). Nothing is ever deleted or hidden from disk. Pass include_archival=false to drop archival hits entirely. Returns {outputs_dir, query, total_indexed, hits:[{path, score, bm25, is_archival, canonical_path, kind, generating_script, csv_columns, json_keys, size, mtime, annotations:[{path, note, run_params, created_at, updated_at, source}]}]}. annotations is auto-included for each hit (any annotation keyed to the hit path OR a nearest ancestor directory) — no second tool call needed. A missing dir / empty tree returns an empty hits list, never an error. 3535b9ad — pass max_seconds to raise/lower the indexing budget (the "indexing slider"): a large or cold tree may not fully converge within the default budget on the first call — the result's partial=true field signals more indexing remains; call again to continue (each call resumes where the last left off, never restarts).

Agent View of the PolicyLayer registry record for `search_outputs`. HTML page: https://policylayer.com/tools/io-github-ajc3xc-meridian/search-outputs

## Facts

- Tool: `search_outputs`
- Server: Meridian (`@meridianmcp/mcp`) — https://policylayer.com/tools/io-github-ajc3xc-meridian.md
- Install: `npx -y @meridianmcp/mcp`
- Homepage: https://github.com/meridianmcp/Meridian
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server CORS policy: *
- Server rate-limited: no
- Parameters: 5 (2 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `limit` | integer | no | Max ranked hits to return (default 10). |
| `query` | string | yes | The BM25 query — one or more search terms (column names, keys, script names, or any text in a csv/json). |
| `max_seconds` | number | no | Wall-clock budget (seconds) for this call's incremental indexing before returning. Omit for the library default. Lower it for a faster first response on a huge |
| `outputs_dir` | string | yes | Absolute path to the outputs directory tree to index and search (walked recursively). |
| `include_archival` | boolean | no | Default true — archival copies are deprioritized but still returned. Set false to exclude confirmed-archival files entirely. |

Parameters from the server's own tool schema.

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

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "search_outputs",
    "arguments": {
      "query": "<query>",
      "outputs_dir": "<outputs_dir>"
    }
  }
}
```

## Why search_outputs is rated Low

This is a read-only search tool that indexes and queries existing output artifacts using full-text search. It retrieves data without any side effects, modifications, or irreversible actions. The explicit '[SUPPORT]' and 'READ-ONLY' designations confirm the read-only nature.

From the tool's own definition: "Tool name: search_outputs; description states '[SUPPORT] a0e9133e — READ-ONLY full-text search over a run's OUTPUTS tree'; 'Walks outputs_dir recursively and builds a persistent index'; 'ranked hits are returned'."

## Use case

AI agents call search_outputs to retrieve information from Meridian 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 Meridian:

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

## Other tools on Meridian (174)

- `archive_decision` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/archive-decision.md
- `batch_mutate` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/batch-mutate.md
- `claim_sprint_item` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/claim-sprint-item.md
- `clear_capability_profile` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/clear-capability-profile.md
- `clone_profile_layer` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/clone-profile-layer.md
- `delete_custom_hook` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/delete-custom-hook.md
- `delete_note` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/delete-note.md
- `delete_sprint_item_pointer` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/delete-sprint-item-pointer.md
- `fan_out_sprint_items` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/fan-out-sprint-items.md
- `purge_ai_log` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/purge-ai-log.md
- `record_handoff_correction` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/record-handoff-correction.md
- `release_docx_region_claims` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/release-docx-region-claims.md
- `request_hitl` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/request-hitl.md
- `reset_plugin_override` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/reset-plugin-override.md
- `reset_profile_layer` — Destructive — https://policylayer.com/tools/io-github-ajc3xc-meridian/reset-profile-layer.md
- `complete_wave_gate` — Execute — https://policylayer.com/tools/io-github-ajc3xc-meridian/complete-wave-gate.md
- `execute_batch` — Execute — https://policylayer.com/tools/io-github-ajc3xc-meridian/execute-batch.md
- `prospect_symbol` — Execute — https://policylayer.com/tools/io-github-ajc3xc-meridian/prospect-symbol.md
- `run_verification` — Execute — https://policylayer.com/tools/io-github-ajc3xc-meridian/run-verification.md
- `start_session` — Execute — https://policylayer.com/tools/io-github-ajc3xc-meridian/start-session.md
- `analyze_model_efficiency` — Read — https://policylayer.com/tools/io-github-ajc3xc-meridian/analyze-model-efficiency.md
- `analyze_sprint` — Read — https://policylayer.com/tools/io-github-ajc3xc-meridian/analyze-sprint.md
- `batch_read` — Read — https://policylayer.com/tools/io-github-ajc3xc-meridian/batch-read.md
- `find_outputs_by_source` — Read — https://policylayer.com/tools/io-github-ajc3xc-meridian/find-outputs-by-source.md
- `find_similar_equation` — Read — https://policylayer.com/tools/io-github-ajc3xc-meridian/find-similar-equation.md
- `find_similar_figure` — Read — https://policylayer.com/tools/io-github-ajc3xc-meridian/find-similar-figure.md
- `find_similar_table` — Read — https://policylayer.com/tools/io-github-ajc3xc-meridian/find-similar-table.md
- `find_symbol_usages` — Read — https://policylayer.com/tools/io-github-ajc3xc-meridian/find-symbol-usages.md
- `get_agent_instructions` — Read — https://policylayer.com/tools/io-github-ajc3xc-meridian/get-agent-instructions.md
- `get_blog_posts` — Read — https://policylayer.com/tools/io-github-ajc3xc-meridian/get-blog-posts.md
- …and 144 more: https://policylayer.com/tools/io-github-ajc3xc-meridian.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=io-github-ajc3xc-meridian · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-ajc3xc-meridian