This record as markdown: /tools/ashlesh-t-cognirepo/search-token.md
What search_token does on CogniRepo
AI agents call search_token to retrieve information from CogniRepo without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why search_token is rated Low
With no explicit description, classification relies on naming conventions and server context. 'Search' operations are typically Read category—retrieving data without side effects. The absence of verbs like 'create', 'delete', 'execute', or 'pay' suggests this retrieves or queries tokens/data.
From the tool's definition Tool name 'search_token' and context of a memory/knowledge server suggest token-based search/retrieval. No description provided, but sibling tools (episodic_search, cross_repo_search) are clearly Read operations.
Attacks that exploit this kind of access
The rule that runs search_token safely
PolicyLayer is an MCP gateway: it sits between your AI agents and CogniRepo, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For search_token, this is the rule to start with:
search_token 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 CogniRepo, apply this rule, and every search_token call is checked against it from then on.
Questions about search_token
search_token is a read tool on the CogniRepo MCP server. It is categorised as a Read tool in the CogniRepo MCP Server, which means it retrieves data without modifying state.
Register the CogniRepo MCP server in PolicyLayer and add a rule for search_token: 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 CogniRepo. Nothing to install.
search_token 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 search_token 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 search_token. 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.
search_token is provided by the CogniRepo MCP server (pypi:cognirepo). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on CogniRepo, and thousands of servers like it.
This server
Across the catalogue