org_wide_search

A read tool on the CogniRepo MCP server.

SERVERCogniRepo SOURCEpypi:cognirepo

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade A, identity unverified Pull the record →

This record as markdown: /tools/ashlesh-t-cognirepo/org-wide-search.md

WHAT IT DOES

What org_wide_search does on CogniRepo

AI agents call org_wide_search 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.

RISK

Why org_wide_search is rated Low

Despite the empty description, the naming pattern and context within a memory/knowledge management MCP server strongly suggests this performs read-only searches across organizational data. No evidence suggests it modifies, deletes, executes code, or commits financial transactions.

From the tool's definition Tool name 'org_wide_search' combined with sibling tools like 'cross_repo_search' and 'episodic_search' indicates this is a search/query tool.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs org_wide_search 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 org_wide_search, this is the rule to start with:

org_wide_search Allowed

org_wide_search is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "org_wide_search": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect CogniRepo, apply this rule, and every org_wide_search call is checked against it from then on.

FAQ

Questions about org_wide_search

What does the org_wide_search tool do? +

org_wide_search 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.

How do I enforce a policy on org_wide_search? +

Register the CogniRepo MCP server in PolicyLayer and add a rule for org_wide_search: 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.

What risk level is org_wide_search? +

org_wide_search is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit org_wide_search? +

Yes. Add a rate_limit block to the org_wide_search 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.

How do I block org_wide_search completely? +

Set action: deny in the PolicyLayer policy for org_wide_search. 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.

What MCP server provides org_wide_search? +

org_wide_search 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.

KEEP EXPLORING

More on CogniRepo, and thousands of servers like it.

This server

All 34 CogniRepo tools →

Across the catalogue

search_torrents on M-Team MCP Server →aiva_search_customers on AIVA MCP Server →search_channel on YouTube MCP Server →hybrid_search on Azure AI Agent Service + Azure AI Search MCP Server → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →