AI agents call ttbz_search_organizations to retrieve information from GBMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'search_' prefix indicates this tool queries and retrieves data about organizations without modifying, deleting, or executing external operations. Although the description is empty, the naming convention and server context (standards metadata queries) strongly suggest a read-only search function.
From the tool's definition Tool name 'ttbz_search_organizations' contains 'search', which is a read-only operation. The tool is part of a standards metadata and document server where sibling tools include 'cfsa_search_standards' and 'doc88_search_documents', both clearly read…
Attacks that exploit this kind of access
ttbz_search_organizations. It is categorised as a Read tool in the GBMCP MCP Server, which means it retrieves data without modifying state.
Register the GB MCP server in PolicyLayer and add a rule for ttbz_search_organizations: 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 GBMCP. Nothing to install.
ttbz_search_organizations 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 ttbz_search_organizations 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 ttbz_search_organizations. 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.
ttbz_search_organizations is provided by the GB MCP server (loydgik/gbmcp). 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 →