// SCAN REPORT

Clodbridge

9 tools. 0 can modify or destroy data without limits.

Read-only server. Low risk, but rate limits prevent runaway API costs.

Last updated: 2 Jul 2026

0 can modify or destroy data

9 read-only

9 tools total

Community server · catalogue entry verified 02/07/2026

How to control Clodbridge ↓

TOOL MAP

What Clodbridge exposes to your agents

Read (9) Write / Execute (0) Destructive / Financial (0)

Running more than one server? Check your whole stack →

THE RISK

What can go wrong

Even read-only tools carry cost. An agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up bills.

POLICY

How to control Clodbridge

PolicyLayer is an MCP gateway — it sits between your AI agents and Clodbridge, and nothing reaches the server without passing your rules. These are the rules we recommend:

Cap read operations

{
  "cursor_get_agent": {
    "limits": [
      {
        "counter": "cursor_get_agent_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Clodbridge — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON CLODBRIDGE →

Instant setup, no code required.

FULL CATALOGUE

All 9 Clodbridge tools

READ 9 tools

Read cursor_get_agent Returns the full definition of a named Cursor agent. Read cursor_get_agent_requested_rules Returns all Cursor rules that are agent-requested (no globs, not alwaysApply). These rules must be explicitly Read cursor_get_always_rules Returns all Cursor rules where alwaysApply is true. These rules should be injected into every conversation. Read cursor_get_applicable_rules Returns all Cursor rules that apply to the given file paths. Includes rules with alwaysApply:true and auto-att Read cursor_get_rule Returns the full content of a named Cursor rule. Read cursor_get_skill Returns the full content of a named Cursor skill. Read cursor_list_agents Lists all available Cursor agents with their names, descriptions, and models. Read cursor_list_rules Lists all available Cursor rules with their names, descriptions, and modes. Read cursor_list_skills Lists all available Cursor skills with their names and descriptions.

FAQ

Questions about Clodbridge

Is the Clodbridge MCP server safe to use without restrictions? +

The Clodbridge server is primarily read-only with 9 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the Clodbridge MCP server expose? +

9 tools across 1 categories: Read. 9 are read-only. 0 can modify, create, or delete data.

How do I enforce a policy on Clodbridge? +

Register the Clodbridge MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Clodbridge tool call.

Deterministic rules across all 9 Clodbridge tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CLODBRIDGE →

Instant setup, no code required.

9 Clodbridge tools catalogued and risk-classified — across an index of 43,000+ MCP servers.