Modelmeter MCP

An MCP server that exposes tools for querying AI model deprecations, pricing, and capabilities, allowing agents to check stack health, estimate costs, and retrieve model details via JSON-RPC.

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.

Vendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-07Operated by Modelmeter

MCP endpoint (Streamable HTTP)

https://modelmeter.xyz/mcp

Vendor documentation

What its tools do

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

Not annotated (7)

estimate_cost
get_model
list_models
get_price_history
list_events
check_model_dependencies
list_deprecations

7 of 7 have a description · 0 of 7 declare behavior hints · 7 of 7 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

Passed Endpoint answered the live check · Nov 7, 2026, 4:26 AM UTC
Passed Official MCP Registry namespace is tied to modelmeter.xyz · Nov 7, 2026, 12:20 AM UTC
Passed Endpoint is on the registry namespace domain · Nov 7, 2026, 12:20 AM UTC
Availability 1 of 1 checks passed in 30 days

What you can do with it

Check if specific models are deprecating or retiring
Estimate the cost of LLM calls given model and token counts
List available models and their current pricing
Retrieve historical pricing data for specific models

Source and maintenance

Vendor evidenceRegistry 1.0.0

mcp-registry: xyz.modelmeter/modelmeter@1.0.0 Source repository Project website

Maintenance checked: Nov 7, 2026, 12:20 AM UTC

Protocol and capabilities

Server: modelmeter 0.1.0
MCP protocol negotiated in check: 2025-06-18
Tools: 7 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {}
}

Server-provided instructions

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

Modelmeter: the changelog of record for the AI stack, agent-callable. check_model_dependencies answers "is my stack okay?" for a list of model ids; list_deprecations shows what dies when. Pricing: start with list_models to discover ids, then get_model or estimate_cost.

Tools

7 advertised

estimate_cost

Advertised by the server during the last successful anonymous check.

Estimate the USD cost of an LLM API call for a given model and token counts. Returns input/output/total cost, plus reseller markup vs. the upstream model when applicable.

estimate_cost input schema

{
  "type": "object",
  "required": [
    "model",
    "input_tokens",
    "output_tokens"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "Model id in provider/model form, e.g. anthropic/claude-opus-4-8. Use list_models to discover ids."
    },
    "input_tokens": {
      "type": "integer",
      "minimum": 0,
      "description": "Number of input (prompt) tokens."
    },
    "output_tokens": {
      "type": "integer",
      "minimum": 0,
      "description": "Number of output (completion) tokens."
    }
  }
}

get_model

Advertised by the server during the last successful anonymous check.

Unified card for one model in a single call: normalized pricing, capabilities (context window, vision, reasoning, tags), availability, reseller markup vs. upstream, and a price-history summary (launch vs. current price, percent change, last change date, all-time low/high).

get_model input schema

{
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Model id in provider/model form, e.g. openai/gpt-5-5."
    }
  }
}

list_models

Advertised by the server during the last successful anonymous check.

List available models with their current pricing. Optionally filter by provider.

list_models input schema

{
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 1000,
      "minimum": 1,
      "description": "Max rows to return. Default 200."
    },
    "provider": {
      "type": "string",
      "description": "Provider id, e.g. anthropic, openai, google, venice, openrouter."
    },
    "include_unavailable": {
      "type": "boolean",
      "description": "Include deprecated/restricted/unavailable models. Default false."
    }
  }
}

get_price_history

Advertised by the server during the last successful anonymous check.

Historical pricing time-series for a model or provider. Each point is a dated snapshot of the per-Mtok rates.

get_price_history input schema

{
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "description": "Model id to fetch history for."
    },
    "since": {
      "type": "string",
      "description": "ISO date (YYYY-MM-DD); only points on/after this date."
    },
    "until": {
      "type": "string",
      "description": "ISO date (YYYY-MM-DD); only points on/before this date."
    },
    "provider": {
      "type": "string",
      "description": "Provider id to fetch history for (all its models)."
    }
  }
}

list_events

Advertised by the server during the last successful anonymous check.

The changelog of record for the model layer: deprecations, price changes, launches, and the market events around them. Filter by severity to find what demands action: 'breaking' (model going away, ID changing), 'action_required' (price/rate-limit/context changes), 'informational' (releases, funding).

list_events input schema

{
  "type": "object",
  "properties": {
    "type": {
      "type": "string",
      "description": "Event type, e.g. model_deprecation, pricing_change, model_launch."
    },
    "limit": {
      "type": "integer",
      "maximum": 500,
      "minimum": 1,
      "description": "Max events. Default 50."
    },
    "since": {
      "type": "string",
      "description": "ISO date (YYYY-MM-DD); events announced on/after."
    },
    "until": {
      "type": "string",
      "description": "ISO date (YYYY-MM-DD); events announced on/before."
    },
    "status": {
      "enum": [
        "verified",
        "unverified",
        "all",
        "corrected"
      ],
      "type": "string",
      "description": "Verification status. Default 'verified' (human-confirmed). 'all' = verified + unverified."
    },
    "provider": {
      "type": "string",
      "description": "Filter to events touching this provider."
    },
    "severity": {
      "enum": [
        "breaking",
        "action_required",
        "informational"
      ],
      "type": "string",
      "description": "Filter by what the event demands of consumers of the affected models."
    }
  }
}

check_model_dependencies

Advertised by the server during the last successful anonymous check.

Is my stack okay? Check a list of model ids against the record: scheduled retirements with days-remaining countdowns and migration targets, past retirements, and other breaking/action-required changes. Id matching tolerates dots vs dashes, dated snapshot suffixes, and bare or provider-prefixed forms. Call this at startup or in CI with the models you depend on.

check_model_dependencies input schema

{
  "type": "object",
  "required": [
    "models"
  ],
  "properties": {
    "models": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 50,
      "minItems": 1,
      "description": "Model ids to check, e.g. [\"gpt-4o\", \"claude-sonnet-4-6\", \"gemini-2.5-flash\"]."
    }
  }
}

list_deprecations

Advertised by the server during the last successful anonymous check.

Per-model retirement rows from the record: which model dies when, with runway and migration target. Default shows scheduled (upcoming) retirements sorted by shutdown date.

list_deprecations input schema

{
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 500,
      "minimum": 1,
      "description": "Max rows. Default 100."
    },
    "status": {
      "enum": [
        "scheduled",
        "retired",
        "all"
      ],
      "type": "string",
      "description": "Default scheduled."
    },
    "provider": {
      "type": "string",
      "description": "Filter to one provider id."
    }
  }
}

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: 542 ms
95th percentile latency: 542 ms

Maintenance history

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

Nov 7, 2026, 4:26 AM UTC · probe · passed · 542 ms · metadata changed · 7 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 modelmeter-mcp https://modelmeter.xyz/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 modelmeter-mcp --url https://modelmeter.xyz/mcp

Cursor

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

Cursor configuration

{
  "mcpServers": {
    "modelmeter-mcp": {
      "url": "https://modelmeter.xyz/mcp"
    }
  }
}

Cline

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

Cline configuration

{
  "mcpServers": {
    "modelmeter-mcp": {
      "type": "streamableHttp",
      "url": "https://modelmeter.xyz/mcp",
      "disabled": false
    }
  }
}

VS Code

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

VS Code configuration

{
  "servers": {
    "modelmeter-mcp": {
      "type": "http",
      "url": "https://modelmeter.xyz/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 modelmeter-mcp https://modelmeter.xyz/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://modelmeter.xyz/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": {
    "modelmeter-mcp": {
      "serverUrl": "https://modelmeter.xyz/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Modelmeter 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

Do you run Modelmeter MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing