query_corpus
Semantic search over YOUR ingested corpus (free local embeddings, cosine top-k), with optional free-LLM synthesis. Owner-gated. Returns {ok, matches[], answer?}.
This record as markdown: /tools/com-wingmanprotocol-agent-gateway/query-corpus.md
What query_corpus does on Gateway
AI agents call query_corpus to retrieve information from Gateway without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
k | integer | — | how many matches (1-8, default 4) |
query | string | Yes | what to search for |
handle | string | Yes | your registered handle |
secret | string | — | your agent secret |
synthesize | boolean | — | also generate a cited answer (free LLM) |
Parameters from the server's own tool schema.
Why query_corpus is rated Low
This tool retrieves and queries data without side effects. It searches an existing corpus and optionally synthesizes answers, but does not create, modify, delete, or execute external operations. This is a classic Read operation. The owner-gating slightly reduces blast radius if credentials were compromised, supporting the low severity assessment.
From the tool's definition Tool performs 'semantic search' and 'returns matches' with optional synthesis. The description explicitly states it queries an 'ingested corpus' and returns search results {ok, matches[], answer?}.
Risk signalsHandles credentials or secrets (secret)
Attacks that exploit this kind of access
The rule that runs query_corpus safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Gateway, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For query_corpus, this is the rule to start with:
query_corpus is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Gateway, apply this rule, and every query_corpus call is checked against it from then on.
Questions about query_corpus
Semantic search over YOUR ingested corpus (free local embeddings, cosine top-k), with optional free-LLM synthesis. Owner-gated. Returns {ok, matches[], answer?}. It is categorised as a Read tool in the Gateway MCP Server, which means it retrieves data without modifying state.
query_corpus accepts 5 parameters: k, query, handle, secret, synthesize. Required: query, handle. The full parameter table on this page comes from the server's own tool schema.
Register the Gateway MCP server in PolicyLayer and add a rule for query_corpus: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Gateway. Nothing to install.
query_corpus is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the query_corpus rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for query_corpus. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
query_corpus is provided by the Gateway MCP server (https://wingmanprotocol.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Gateway, and thousands of servers like it.
This server
Across the catalogue