Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 4,676 across 1213 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confide...
AI agents call ask_pipeworx_grounded to retrieve information from Mcp Va Museum without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
q | string | — | Alias for question. |
text | string | — | Alias for question. |
input | string | — | Alias for question. |
query | string | — | Alias for question. |
prompt | string | — | Alias for question. |
question | string | Yes | Your question in natural language. Accepts query, q, prompt, text, input as aliases. |
Parameters from the server's own tool schema.
This tool queries and retrieves data from museum collections and sources without modifying, executing code, or producing side effects. The description explicitly characterizes it as a 'read' operation that 'fetches the data' and 'extracts the answer', with safeguards against hallucination. No creation, deletion, or execution of external operations is described.
From the tool's definition Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 4,676 across 1213 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains.
Risk signalsAccepts freeform code/query input (query)
Attacks that exploit this kind of access
Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 4,676 across 1213 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups. It is categorised as a Read tool in the Mcp Va Museum MCP Server, which means it retrieves data without modifying state.
ask_pipeworx_grounded accepts 6 parameters: q, text, input, query, prompt, question. Required: question. The full parameter table on this page comes from the server's own tool schema.
Register the Mcp Va Museum MCP server in PolicyLayer and add a rule for ask_pipeworx_grounded: 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 Mcp Va Museum. Nothing to install.
ask_pipeworx_grounded 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 ask_pipeworx_grounded 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 ask_pipeworx_grounded. 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.
ask_pipeworx_grounded is provided by the Mcp Va Museum MCP server (pipeworx-io/mcp-va-museum). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →