// SCAN REPORT

Agent Cost

6 tools. 2 can modify or destroy data without limits.

2 write tools that can modify data. Rate limits recommended.

Last updated: 30 Jun 2026

2 can modify or destroy data

4 read-only

6 tools total

Community server · catalogue entry verified 30/06/2026

How to control Agent Cost ↓

TOOL MAP

What Agent Cost exposes to your agents

Read (4) Write / Execute (2) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Agent Cost tools

Write · Medium set_budget This tool modifies budget configuration settings, which is a reversible write operation. Write · Medium log_cost This tool writes cost and token usage records to the tracking system after each AI interaction.

2 of Agent Cost's 6 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Agent Cost

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

Rate limit write operations

{
  "log_cost": {
    "limits": [
      {
        "counter": "log_cost_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "cost_report": {
    "limits": [
      {
        "counter": "cost_report_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 Agent Cost — 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 AGENT COST →

Instant setup, no code required.

FULL CATALOGUE

All 6 Agent Cost tools

WRITE 2 tools

Write log_cost Log token usage and cost for a task. Call this after each AI interaction. Write set_budget Set daily and/or monthly budget limits.

READ 4 tools

Read cost_report Get a spending report. Read cost_trend Show daily spending trend as a text chart. Read estimate_cost Estimate cost without logging it. Use for planning. Read supported_models List all supported models and their pricing.

FAQ

Questions about Agent Cost

How do I prevent bulk modifications through Agent Cost? +

The Agent Cost server has 2 write tools including log_cost, set_budget. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Agent Cost.

How many tools does the Agent Cost MCP server expose? +

6 tools across 2 categories: Read, Write. 4 are read-only. 2 can modify, create, or delete data.

How do I enforce a policy on Agent Cost? +

Register the Agent Cost 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 Agent Cost tool call.

Deterministic rules across all 6 Agent Cost tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON AGENT COST →

Instant setup, no code required.

6 Agent Cost tools catalogued and risk-classified — across an index of 43,000+ MCP servers.