grant_agent_tool

SERVERFreedom Mcp SOURCEhttps://twuluxmoognlwtmaoqgo.supabase.co/functions/v1/freedom-mcp

Medium RISK CLASS

Category Write

Parameters 43 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/com-getfreedomos-freedom-mcp/grant-agent-tool.md

WHAT IT DOES

What grant_agent_tool does on Freedom Mcp

AI agents use grant_agent_tool to create or update resources in Freedom Mcp, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Freedom Mcp environment.

Parameter	Type	Required	Description
`reason`	string	—	Optional one-line why — stored in the audit record on the agent's JD.
`agent_id`	string	Yes	UUID of the agent receiving the tool. Use get_team_roster to find IDs.
`companyId`	string	Yes	FreedomOS company id to act within (you must be a member). Required for company-scoped tools.
`tool_name`	string	Yes	Exact registry name of the tool to grant (e.g. "capture_idea").

Parameters from the server's own tool schema.

RISK

Why grant_agent_tool is rated Medium

This tool modifies agent capabilities by granting tool access, which is a reversible write operation affecting authorization state. The severity is high because granting malicious or powerful tools to an agent could enable harmful downstream actions. It does not delete (not Destructive), does not move money (not Financial), and does not directly execute code (not Execute) — it configures permissions.

From the tool's definition Tool grants/assigns a specific tool to an agent's loadout (tool_access), modifying the agent's capabilities. Description explicitly states "use when an operator says 'give <agent> the <tool> tool'" — a create/modify operation on agent permissions.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs grant_agent_tool safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Freedom Mcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For grant_agent_tool, this is the rule to start with:

grant_agent_tool Rate-limited

grant_agent_tool stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "grant_agent_tool": {
      "limits": [
        {
          "counter": "grant_agent_tool_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

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

FAQ

Questions about grant_agent_tool

What does the grant_agent_tool tool do? +

Grant ONE specific tool to an agent's loadout (tool_access). Use when an operator says "give <agent> the <tool> tool" / "let <agent> use <tool>". The tool name is validated against the live registry at write time — phantom names are rejected, deprecated names auto-map to their successor. For wholesale capability re-derivation use recalibrate_agent_jd instead; connector tools auto-provision on connection. [sensitive-tier — first use may require a manager's approval; a from-now-on approval makes future calls seamless, a just-once approval re-asks next time.]. It is categorised as a Write tool in the Freedom Mcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does grant_agent_tool accept? +

grant_agent_tool accepts 4 parameters: reason, agent_id, companyId, tool_name. Required: agent_id, companyId, tool_name. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on grant_agent_tool? +

Register the Freedom MCP server in PolicyLayer and add a rule for grant_agent_tool: 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 Freedom Mcp. Nothing to install.

What risk level is grant_agent_tool? +

grant_agent_tool is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit grant_agent_tool? +

Yes. Add a rate_limit block to the grant_agent_tool 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 grant_agent_tool completely? +

Set action: deny in the PolicyLayer policy for grant_agent_tool. 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 grant_agent_tool? +

grant_agent_tool is provided by the Freedom MCP server (https://twuluxmoognlwtmaoqgo.supabase.co/functions/v1/freedom-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Freedom, and thousands of servers like it.

This server

All 238 Freedom tools →

Across the catalogue

team_manager_kill_agent on Team Manager MCP → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →