Free tool · #19

MCP Schema Token-Cost Validator

See how many tokens your MCP tool schemas add to every request — and what that overhead costs.

Prices verified 15 Jul 2026 · 131 models

Consuming model701 models

tools/list JSON

{
  "tools": [
    {
      "name": "search_files",
      "description": "Search the workspace for files whose contents match a query. Returns ranked file paths with matching line snippets. Use for \"where is X\" questions before reading whole files.",
      "inputSchema": {
        "type": "object",
        "properties": {
          "query": {
            "type": "string",
            "description": "The search query (plain text or regex)."
          },
          "path": {
            "type": "string",
            "description": "Directory to search within. Defaults to the workspace root."
          },
          "max_results": {
            "type": "integer",
            "description": "Maximum number of results to return.",
            "default": 20
          }
        },
        "required": [
          "query"
        ]
      }
    },
    {
      "name": "read_file",
      "description": "Read a file from the workspace and return its contents, optionally a line range.",
      "inputSchema": {
        "type": "object",
        "properties": {
          "path": {
            "type": "string",
            "description": "Absolute path to the file to read."
          },
          "offset": {
            "type": "integer",
            "description": "Line number to start reading from."
          },
          "limit": {
            "type": "integer",
            "description": "Number of lines to read."
          }
        },
        "required": [
          "path"
        ]
      }
    }
  ]
}

Per-request token overhead

200tokens / request

exacttiktoken o200k_base

≈ $0.00050 / request · $500.00 per 1M requests · openai · gpt-4o

Tool	Tokens	/ request
search_files	114	$0.00029
read_file	86	$0.00022

Approximate — counted from the JSON serialization of your schemas; the exact overhead depends on how your client formats tools for the model.

Use this tool from code — or hand it to your agentagent prompt · REST · MCP

Hand this tool to your coding agent

Paste into Claude Code, Cursor, Codex, or any agent. It learns to call this tool over REST or MCP, reaches for it when you ask, and keeps our sourced/pending labels honest.

You can use telemeter.ai's free "MCP Schema Token-Cost Validator" — a keyless, read-only tool (no signup), available as an HTTP API and an MCP tool. What it does: See how many tokens your MCP tool schemas add to every request — and what that overhead costs.

Whenever I ask you something this tool answers, call it and use its result instead of estimating yourself.

REST:
  curl -sX POST https://telemeter.ai/api/tools/mcp-schema-token-cost -H 'content-type: application/json' -d '{"model":"gpt-4o","toolsJson":"{\"tools\":[{\"name\":\"search_files\",\"description\":\"Search the workspace for files whose contents match a query.\",\"inputSchema\":{\"type\":\"object\",\"properties\":{\"query\":{\"type\":\"string\",\"description\":\"The search query (plain text or regex).\"}},\"required\":[\"query\"]}}]}"}'

MCP: the telemeter MCP server at https://telemeter.ai/mcp exposes this as the tool "mcp-schema-token-cost" — call it with tools/call.

The response is JSON: { status, data, summary, provenance }. "provenance" carries the source and the date the figure was verified. If status is "pending" or "stale", tell me the value isn't currently verified rather than presenting it as fact.

Or call it directly. This tool runs behind one handler with three front doors — this page, a REST endpoint, and an MCP tool. Same result, read-only, no key. The example below is a request that works.

REST

curl -sX POST https://telemeter.ai/api/tools/mcp-schema-token-cost \
  -H 'content-type: application/json' \
  -d '{"model":"gpt-4o","toolsJson":"{\"tools\":[{\"name\":\"search_files\",\"description\":\"Search the workspace for files whose contents match a query.\",\"inputSchema\":{\"type\":\"object\",\"properties\":{\"query\":{\"type\":\"string\",\"description\":\"The search query (plain text or regex).\"}},\"required\":[\"query\"]}}]}"}'

MCP — tools/call at https://telemeter.ai/mcp

curl -sX POST https://telemeter.ai/mcp \
  -H 'content-type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"mcp-schema-token-cost","arguments":{"model":"gpt-4o","toolsJson":"{\"tools\":[{\"name\":\"search_files\",\"description\":\"Search the workspace for files whose contents match a query.\",\"inputSchema\":{\"type\":\"object\",\"properties\":{\"query\":{\"type\":\"string\",\"description\":\"The search query (plain text or regex).\"}},\"required\":[\"query\"]}}]}"}}}'

Input schema (JSON Schema)

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "minLength": 1
    },
    "toolsJson": {
      "type": "string",
      "minLength": 1,
      "maxLength": 600000
    }
  },
  "required": [
    "model",
    "toolsJson"
  ],
  "additionalProperties": false
}

Want this across your whole stack?

Telemeter tracks real cost, latency, and quality on every production agent run — on the same verified pricing behind this tool.

Join the waitlist See how it works

Share or cite this tool

https://telemeter.ai/tools/mcp-schema-token-cost

No account — the schema you paste is counted on our server and never stored or logged. Data notice →