query_company_knowledge
Search this company's reviewed knowledge base and return grounded snippets with source document IDs. Use for merchant policies, FAQs, pricing notes, brand guidance, and other uploaded references.
This record as markdown: /tools/io-favcrm-favcrm/query-company-knowledge.md
What query_company_knowledge does on FavCRM
AI agents call query_company_knowledge to retrieve information from FavCRM 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 |
|---|---|---|---|
limit | integer | — | Maximum matching snippets (default 5) |
query | string | Yes | Question or keywords to search for in company knowledge |
maxSnippetChars | integer | — | Maximum characters per snippet (default 600) |
Parameters from the server's own tool schema.
Why query_company_knowledge is rated Low
This tool retrieves and queries existing data (company knowledge, policies, FAQs, pricing) without creating, modifying, deleting, or executing anything. It is purely informational and read-only. The low severity reflects that misuse results only in information disclosure of internal knowledge already stored in the company system, not unauthorized external data exfiltration or destructive action.
From the tool's definition Tool performs a 'Search' operation on a 'knowledge base' and 'return[s] grounded snippets' — a retrieval action with no modification or side effects.
Attacks that exploit this kind of access
The rule that runs query_company_knowledge safely
PolicyLayer is an MCP gateway: it sits between your AI agents and FavCRM, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For query_company_knowledge, this is the rule to start with:
query_company_knowledge 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 FavCRM, apply this rule, and every query_company_knowledge call is checked against it from then on.
Questions about query_company_knowledge
Search this company's reviewed knowledge base and return grounded snippets with source document IDs. Use for merchant policies, FAQs, pricing notes, brand guidance, and other uploaded references. It is categorised as a Read tool in the FavCRM MCP Server, which means it retrieves data without modifying state.
query_company_knowledge accepts 3 parameters: limit, query, maxSnippetChars. Required: query. The full parameter table on this page comes from the server's own tool schema.
Register the FavCRM MCP server in PolicyLayer and add a rule for query_company_knowledge: 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 FavCRM. Nothing to install.
query_company_knowledge 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_company_knowledge 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_company_knowledge. 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_company_knowledge is provided by the FavCRM MCP server (https://api.favcrm.io/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on FavCRM, and thousands of servers like it.
This server
Across the catalogue