# search_within

Semantic search INSIDE a fetched record. Pass the text you already pulled (e.g. a SEC 10-K body, an article, a long tool result) plus a natural-language query; get back the top-N passages with character offsets and similarity scores. Use when the record is too big to cram into the prompt — search_within saves context, returns only the passages that matter, and every passage carries an offset so the agent can verify a verbatim quote. Pairs with ask_pipeworx_grounded: fetch with the gateway, ground over the relevant passages instead of the whole document. BGE-base-en embeddings + cosine over 500-char overlapping windows; cap is 200K chars (longer inputs are truncated and flagged).

Agent View of the PolicyLayer registry record for `search_within`. HTML page: https://policylayer.com/tools/io-github-pipeworx-io-linear/search-within

## Facts

- Tool: `search_within`
- Server: Linear (`https://gateway.pipeworx.io/linear/mcp`) — https://policylayer.com/tools/io-github-pipeworx-io-linear.md
- Homepage: https://github.com/pipeworx-io/mcp-linear
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server CORS policy: *
- Server rate-limited: yes
- Parameters: 3 (2 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `text` | string | yes | The document text to search inside (max ~200K chars). |
| `limit` | number | no | Max passages to return (1-20, default 5). |
| `query` | string | yes | Natural-language query — what passages do you want? E.g. "supply-chain risk", "fiscal year 2024 revenue", "drug interactions with warfarin". |

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_within",
    "arguments": {
      "text": "<text>",
      "query": "<query>"
    }
  }
}
```

## Why search_within is rated Low

The tool performs semantic search over already-fetched text and returns filtered passages with metadata (offsets, scores). It does not modify, delete, execute code, or move data. It is purely a Read operation that retrieves and queries information from a document the user has already obtained.

From the tool's own definition: "Semantic search INSIDE a fetched record. Pass the text you already pulled... get back the top-N passages with character offsets and similarity scores... search_within saves context, returns only the passages that matter."

Risk signals: Bulk/mass operation — affects multiple targets

## Use case

AI agents call search_within to retrieve information from Linear 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 Linear:

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

## Other tools on Linear (35)

- `forget` — Destructive — https://policylayer.com/tools/io-github-pipeworx-io-linear/forget.md
- `generate_llms_txt` — Execute — https://policylayer.com/tools/io-github-pipeworx-io-linear/generate-llms-txt.md
- `polymarket_edges` — Financial — https://policylayer.com/tools/io-github-pipeworx-io-linear/polymarket-edges.md
- `polymarket_fill_risk` — Financial — https://policylayer.com/tools/io-github-pipeworx-io-linear/polymarket-fill-risk.md
- `ai_visibility_check` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/ai-visibility-check.md
- `ask_pipeworx` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/ask-pipeworx.md
- `ask_pipeworx_beta` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/ask-pipeworx-beta.md
- `ask_pipeworx_grounded` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/ask-pipeworx-grounded.md
- `bet_research` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/bet-research.md
- `compare_entities` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/compare-entities.md
- `deep_research` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/deep-research.md
- `discover_tools` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/discover-tools.md
- `entity_profile` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/entity-profile.md
- `linear_get_issue` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/linear-get-issue.md
- `linear_list_issues` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/linear-list-issues.md
- `linear_list_teams` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/linear-list-teams.md
- `linear_search` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/linear-search.md
- `list_subscriptions` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/list-subscriptions.md
- `pipeworx_trending` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/pipeworx-trending.md
- `polymarket_arbitrage` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/polymarket-arbitrage.md
- `polymarket_edge_tracker` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/polymarket-edge-tracker.md
- `polymarket_kalshi_spread` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/polymarket-kalshi-spread.md
- `recall` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/recall.md
- `recent_alerts` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/recent-alerts.md
- `recent_changes` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/recent-changes.md
- `resolve_entity` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/resolve-entity.md
- `scan_competitor_ai_presence` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/scan-competitor-ai-presence.md
- `scan_dependency` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/scan-dependency.md
- `suggest_questions` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/suggest-questions.md
- `validate_claim` — Read — https://policylayer.com/tools/io-github-pipeworx-io-linear/validate-claim.md
- …and 5 more: https://policylayer.com/tools/io-github-pipeworx-io-linear.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-pipeworx-io-linear · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-pipeworx-io-linear