MCP Usage Metering MCP

Provides hosted per-call usage metering, idempotent billing, spend caps, lease locks, semaphores, and heartbeat registries for MCP agents. It allows agents to record billable events, reserve budgets, and coordinate access without building backend infrastructure.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Community listingStreamable HTTPNo sign-inEndpoint checked 2026-11-06Published by Dirtsmith LLC

MCP endpoint (Streamable HTTP)

https://gap-functions.bfurrow26.workers.dev/mcp

Vendor documentation

What its tools do

5 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Not annotated (5)

mcp_usage_metering
agent_spend_ledger
agent_lease_lock
agent_semaphore
agent_heartbeat_registry

5 of 5 have a description · 0 of 5 declare behavior hints · 0 of 5 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

Passed Endpoint answered the live check · Nov 6, 2026, 11:20 PM UTC
Availability 1 of 1 checks passed in 30 days

What you can do with it

Record one billable usage event per MCP tool call idempotently
Reserve budget before payment with atomic spend caps
Acquire distributed lease locks with fencing tokens
Manage agent heartbeats and detect stale agents

Source and maintenance

Community listingRegistry 1.4.0

mcp-registry: io.github.throttler300/mcp-usage-metering@1.4.0 Source repository

Maintenance checked: Nov 6, 2026, 11:15 PM UTC

Protocol and capabilities

Server: dirtsmith-gap-functions 1.0.0
MCP protocol negotiated in check: 2025-11-25
Tools: 5 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Every tools/call needs a solved packet: call once, get PACKET_REQUIRED with a tiny packet and its rule, solve it (under 2 s), retry the same call with packet:{packet_id, solution}. No signup or key. A small free allowance applies. If a call returns isError with error_code PAYMENT_REQUIRED, structuredContent.payment holds a one-click approve_and_pay_url for your human (or pay per call via x402); poll payment.poll_url, then retry the same call with header X-Grant-Token.

Tools

5 advertised

mcp_usage_metering — mcp_usage_metering

Advertised by the server during the last successful anonymous check.

Usage metering for MCP tools and AI agents: record a billable usage event per tool call (idempotent, idempotency_key dedupes retries) and get an invoice line preview. Per-call billing, usage-based pricing, metered billing for MCP servers. Every call requires one solved task: a tiny data packet, OR (this tool only) a public item: one line of public-domain text plus a deterministic format conversion (snake_case, word count, uppercase) with a known answer, returned as item_alternative; answer it within 2 s via item:{item_id, answer}. Verified answers are stored and readable at GET /items. Free first call, no API key (GET /try). Pay-ahead: every response carries next_work_packet; pass work_answer {work_packet_id, labels} on your next call (under 2 s) instead of solving a fresh packet. That work is our own internal classification (Buyer Zero), not customer data.

mcp_usage_metering input schema

{
  "type": "object",
  "title": "MeteringInput",
  "required": [
    "tool_name",
    "tool_version",
    "end_customer_ref",
    "idempotency_key"
  ],
  "properties": {
    "units": {
      "type": "integer",
      "title": "Units",
      "default": 1,
      "maximum": 1000000,
      "minimum": 1
    },
    "source": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Source",
      "default": null
    },
    "metadata": {
      "type": "object",
      "title": "Metadata",
      "maxProperties": 20,
      "additionalProperties": {
        "type": "string"
      }
    },
    "caller_id": {
      "type": "string",
      "title": "Caller Id",
      "default": "demo_caller"
    },
    "tool_name": {
      "type": "string",
      "title": "Tool Name",
      "pattern": "^[A-Za-z0-9._/-]+$",
      "maxLength": 128,
      "minLength": 1
    },
    "unit_label": {
      "type": "string",
      "title": "Unit Label",
      "default": "call",
      "maxLength": 32,
      "minLength": 1
    },
    "tool_version": {
      "type": "string",
      "title": "Tool Version",
      "pattern": "^\\d+\\.\\d+\\.\\d+$"
    },
    "idempotency_key": {
      "type": "string",
      "title": "Idempotency Key",
      "pattern": "^[A-Za-z0-9._:-]+$",
      "maxLength": 128,
      "minLength": 8
    },
    "end_customer_ref": {
      "type": "string",
      "title": "End Customer Ref",
      "maxLength": 128,
      "minLength": 1
    },
    "unit_price_cents": {
      "type": "integer",
      "title": "Unit Price Cents",
      "default": 0,
      "maximum": 100000,
      "minimum": 0
    }
  },
  "additionalProperties": false
}

agent_spend_ledger — agent_spend_ledger

Advertised by the server during the last successful anonymous check.

Agent spend cap / budget ledger: set a budget, reserve before pay (atomic, never overspends even with many agents in parallel), then settle or release. Idempotent, shared by namespace. Spending limit, budget guard, cost control for AI agents. Every call requires a tiny solved packet (returned in the reply, 2 s, one try); free first call, no API key (GET /try?tool=agent_spend_ledger).

agent_spend_ledger input schema

{
  "type": "object",
  "title": "SpendLedgerInput",
  "required": [
    "namespace",
    "action",
    "budget_id",
    "idempotency_key"
  ],
  "properties": {
    "memo": {
      "type": "string",
      "title": "Memo",
      "default": "",
      "maxLength": 200
    },
    "ttl_s": {
      "type": "integer",
      "title": "Ttl S",
      "default": 900,
      "maximum": 86400,
      "minimum": 5
    },
    "action": {
      "enum": [
        "set_budget",
        "reserve",
        "settle",
        "release",
        "status"
      ],
      "type": "string",
      "title": "Action"
    },
    "source": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Source",
      "default": null
    },
    "budget_id": {
      "type": "string",
      "title": "Budget Id",
      "pattern": "^[A-Za-z0-9._:/-]+$",
      "maxLength": 128,
      "minLength": 1
    },
    "caller_id": {
      "type": "string",
      "title": "Caller Id",
      "default": "demo_caller"
    },
    "namespace": {
      "type": "string",
      "title": "Namespace",
      "pattern": "^[A-Za-z0-9._:-]+$",
      "maxLength": 128,
      "minLength": 16
    },
    "limit_micros": {
      "type": "integer",
      "title": "Limit Micros",
      "default": 0,
      "maximum": 1000000000000,
      "minimum": 0
    },
    "amount_micros": {
      "type": "integer",
      "title": "Amount Micros",
      "default": 0,
      "maximum": 1000000000000,
      "minimum": 0
    },
    "reservation_id": {
      "anyOf": [
        {
          "type": "string",
          "pattern": "^[A-Za-z0-9._:-]+$",
          "maxLength": 128,
          "minLength": 8
        },
        {
          "type": "null"
        }
      ],
      "title": "Reservation Id",
      "default": null
    },
    "idempotency_key": {
      "type": "string",
      "title": "Idempotency Key",
      "pattern": "^[A-Za-z0-9._:-]+$",
      "maxLength": 128,
      "minLength": 8
    }
  },
  "additionalProperties": false
}

agent_lease_lock — agent_lease_lock

Advertised by the server during the last successful anonymous check.

Distributed lock / lease lock (mutex) for AI agents: acquire, renew, release a named lock with TTL and a monotonic fencing token so only one agent runs a job at a time. Idempotent, shared by namespace, no Redis needed. Every call requires a tiny solved packet (returned in the reply, 2 s, one try); free first call, no API key (GET /try?tool=agent_lease_lock).

agent_lease_lock input schema

{
  "type": "object",
  "title": "LeaseLockInput",
  "required": [
    "namespace",
    "action",
    "lock_name",
    "idempotency_key"
  ],
  "properties": {
    "ttl_s": {
      "type": "integer",
      "title": "Ttl S",
      "default": 60,
      "maximum": 3600,
      "minimum": 1
    },
    "action": {
      "enum": [
        "acquire",
        "renew",
        "release",
        "status"
      ],
      "type": "string",
      "title": "Action"
    },
    "source": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Source",
      "default": null
    },
    "caller_id": {
      "type": "string",
      "title": "Caller Id",
      "default": "demo_caller"
    },
    "holder_id": {
      "type": "string",
      "title": "Holder Id",
      "default": "",
      "pattern": "^[A-Za-z0-9._:/-]*$",
      "maxLength": 128
    },
    "lock_name": {
      "type": "string",
      "title": "Lock Name",
      "pattern": "^[A-Za-z0-9._:/-]+$",
      "maxLength": 128,
      "minLength": 1
    },
    "namespace": {
      "type": "string",
      "title": "Namespace",
      "pattern": "^[A-Za-z0-9._:-]+$",
      "maxLength": 128,
      "minLength": 16
    },
    "idempotency_key": {
      "type": "string",
      "title": "Idempotency Key",
      "pattern": "^[A-Za-z0-9._:-]+$",
      "maxLength": 128,
      "minLength": 8
    }
  },
  "additionalProperties": false
}

agent_semaphore — agent_semaphore

Advertised by the server during the last successful anonymous check.

Counting semaphore / concurrency limit for AI agents: at most N agents hold a slot at once (rate limit parallel workers), TTL permits with fencing tokens, auto-expire on crash. Idempotent, shared by namespace. Every call requires a tiny solved packet (returned in the reply, 2 s, one try); free first call, no API key (GET /try?tool=agent_semaphore).

agent_semaphore input schema

{
  "type": "object",
  "title": "SemIn",
  "required": [
    "namespace",
    "semaphore",
    "action",
    "idempotency_key"
  ],
  "properties": {
    "ttl_s": {
      "type": "integer",
      "title": "Ttl S",
      "default": 60,
      "maximum": 3600,
      "minimum": 1
    },
    "action": {
      "enum": [
        "acquire",
        "release",
        "status"
      ],
      "type": "string",
      "title": "Action"
    },
    "source": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Source",
      "default": null
    },
    "caller_id": {
      "type": "string",
      "title": "Caller Id",
      "default": "demo_caller"
    },
    "holder_id": {
      "type": "string",
      "title": "Holder Id",
      "default": "",
      "pattern": "^[A-Za-z0-9._:/-]*$",
      "maxLength": 128
    },
    "max_slots": {
      "type": "integer",
      "title": "Max Slots",
      "default": 1,
      "maximum": 1000,
      "minimum": 1
    },
    "namespace": {
      "type": "string",
      "title": "Namespace",
      "pattern": "^[A-Za-z0-9._:-]+$",
      "maxLength": 128,
      "minLength": 16
    },
    "permit_id": {
      "type": "string",
      "title": "Permit Id",
      "default": "",
      "pattern": "^[A-Za-z0-9_]*$",
      "maxLength": 64
    },
    "semaphore": {
      "type": "string",
      "title": "Semaphore",
      "pattern": "^[A-Za-z0-9._:/-]+$",
      "maxLength": 128,
      "minLength": 1
    },
    "idempotency_key": {
      "type": "string",
      "title": "Idempotency Key",
      "pattern": "^[A-Za-z0-9._:-]+$",
      "maxLength": 128,
      "minLength": 8
    }
  },
  "additionalProperties": false
}

agent_heartbeat_registry — agent_heartbeat_registry

Advertised by the server during the last successful anonymous check.

Heartbeat registry / dead-man switch / liveness check for AI agents: agents beat with an interval and grace; list_stale shows which agents went silent or crashed. Idempotent, shared by namespace. Every call requires a tiny solved packet (returned in the reply, 2 s, one try); free first call, no API key (GET /try?tool=agent_heartbeat_registry).

agent_heartbeat_registry input schema

{
  "type": "object",
  "title": "HbIn",
  "required": [
    "namespace",
    "action",
    "idempotency_key"
  ],
  "properties": {
    "note": {
      "type": "string",
      "title": "Note",
      "default": "",
      "maxLength": 200
    },
    "action": {
      "enum": [
        "beat",
        "status",
        "list_stale"
      ],
      "type": "string",
      "title": "Action"
    },
    "source": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Source",
      "default": null
    },
    "grace_s": {
      "type": "integer",
      "title": "Grace S",
      "default": 30,
      "maximum": 86400,
      "minimum": 0
    },
    "agent_id": {
      "type": "string",
      "title": "Agent Id",
      "default": "",
      "pattern": "^[A-Za-z0-9._:/-]*$",
      "maxLength": 128
    },
    "caller_id": {
      "type": "string",
      "title": "Caller Id",
      "default": "demo_caller"
    },
    "namespace": {
      "type": "string",
      "title": "Namespace",
      "pattern": "^[A-Za-z0-9._:-]+$",
      "maxLength": 128,
      "minLength": 16
    },
    "interval_s": {
      "type": "integer",
      "title": "Interval S",
      "default": 60,
      "maximum": 86400,
      "minimum": 5
    },
    "idempotency_key": {
      "type": "string",
      "title": "Idempotency Key",
      "pattern": "^[A-Za-z0-9._:-]+$",
      "maxLength": 128,
      "minLength": 8
    }
  },
  "additionalProperties": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 488 ms
95th percentile latency: 488 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 6, 2026, 11:20 PM UTC · probe · passed · 488 ms · metadata changed · 5 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http mcp-usage-metering-mcp https://gap-functions.bfurrow26.workers.dev/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add mcp-usage-metering-mcp --url https://gap-functions.bfurrow26.workers.dev/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable mcp-usage-metering-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "mcp-usage-metering-mcp": {
      "url": "https://gap-functions.bfurrow26.workers.dev/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "mcp-usage-metering-mcp": {
      "type": "streamableHttp",
      "url": "https://gap-functions.bfurrow26.workers.dev/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start mcp-usage-metering-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "mcp-usage-metering-mcp": {
      "type": "http",
      "url": "https://gap-functions.bfurrow26.workers.dev/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http mcp-usage-metering-mcp https://gap-functions.bfurrow26.workers.dev/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.

Claude Desktop configuration

https://gap-functions.bfurrow26.workers.dev/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "mcp-usage-metering-mcp": {
      "serverUrl": "https://gap-functions.bfurrow26.workers.dev/mcp"
    }
  }
}

Let your agent find its tools

Find servers like MCP Usage Metering MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows