Koskamo

Agent Cost Hub MCP

This MCP server provides read-only tools for AI agents to look up daily-verified LLM API prices and calculate estimated monthly costs for various AI agent workloads. It allows users to list models, get specific pricing, estimate costs based on usage, and compare models side-by-side without requiring authentication.

Visit Agent Cost Hub

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.

Agent Cost Hub MCP logo, by Agent Cost HubVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by Agent Cost Hub
MCP endpoint (Streamable HTTP)
https://agentcosthub.com/mcp
Vendor documentation

What you can do with it

  • Look up current prices for LLM models per 1M tokens
  • Estimate monthly costs for specific AI agent workloads
  • Compare pricing between multiple AI models
  • Find the cheapest models for specific use cases like RAG or chatbots

Source and maintenance

Vendor evidenceRegistry 1.0.0
mcp-registry: com.agentcosthub/agent-cost-hub@1.0.0Project website

Protocol and capabilities

Server
agentcosthub 0.1.0
MCP protocol
2025-06-18
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.

Read-only LLM API price data and agent cost estimates from agentcosthub.com. Prices last verified 1 Nov 2026 (2026-11-01).

Tools

5 advertised

list_models — List models
Advertised by the server during the last successful anonymous check.
Advertised read-only

List LLMs tracked by Agent Cost Hub with API list prices per 1M tokens. Optional filter by provider or text.

list_models input schema
{
  "type": "object",
  "properties": {
    "search": {
      "type": "string"
    },
    "provider": {
      "type": "string",
      "description": "e.g. openai, anthropic, google"
    },
    "popular_only": {
      "type": "boolean"
    }
  }
}
list_models annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
get_model_price — Get model price
Advertised by the server during the last successful anonymous check.
Advertised read-only

Current API list price of one model (input, output, cached input per 1M tokens) plus example monthly agent costs.

get_model_price input schema
{
  "type": "object",
  "required": [
    "model"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "Model id like anthropic/claude-sonnet-5.5, or a name"
    }
  }
}
get_model_price annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
estimate_cost — Estimate agent cost
Advertised by the server during the last successful anonymous check.
Advertised read-only

Estimate the monthly API cost of an AI agent or chatbot on one model. Easiest: pass model + preset (chatbot, rag, coding_agent, research_agent). Or give input_tokens, output_tokens and calls_per_day (plus optional steps_per_task, cached_percent); explicit numbers override the preset.

estimate_cost input schema
{
  "type": "object",
  "required": [
    "model"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "Model id like anthropic/claude-sonnet-5.5, or a name like \"Grok 4.7\""
    },
    "preset": {
      "enum": [
        "chatbot",
        "rag",
        "coding_agent",
        "research_agent"
      ],
      "type": "string",
      "description": "Optional workload preset that fills in token defaults: chatbot, rag, coding_agent, research_agent. Explicit numbers override it."
    },
    "input_tokens": {
      "type": "number",
      "description": "Input tokens per call/step"
    },
    "calls_per_day": {
      "type": "number",
      "description": "Calls (or agent tasks) per day"
    },
    "output_tokens": {
      "type": "number",
      "description": "Output tokens per call/step"
    },
    "cached_percent": {
      "type": "number",
      "description": "Share of input billed at the cached price, 0-100 (default 50 if steps_per_task>1, else 0)"
    },
    "steps_per_task": {
      "type": "number",
      "description": "Model calls per task for multi-step agents (default 1)"
    }
  }
}
estimate_cost annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
compare_models — Compare models
Advertised by the server during the last successful anonymous check.
Advertised read-only

Compare 2-5 models on price and (optionally) on the monthly cost of one workload.

compare_models input schema
{
  "type": "object",
  "required": [
    "models"
  ],
  "properties": {
    "models": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 5,
      "minItems": 2
    },
    "preset": {
      "enum": [
        "chatbot",
        "rag",
        "coding_agent",
        "research_agent"
      ],
      "type": "string",
      "description": "Optional workload preset that fills in token defaults: chatbot, rag, coding_agent, research_agent. Explicit numbers override it."
    },
    "input_tokens": {
      "type": "number",
      "description": "Input tokens per call/step"
    },
    "calls_per_day": {
      "type": "number",
      "description": "Calls (or agent tasks) per day"
    },
    "output_tokens": {
      "type": "number",
      "description": "Output tokens per call/step"
    },
    "cached_percent": {
      "type": "number",
      "description": "Share of input billed at the cached price, 0-100 (default 50 if steps_per_task>1, else 0)"
    },
    "steps_per_task": {
      "type": "number",
      "description": "Model calls per task for multi-step agents (default 1)"
    }
  }
}
compare_models annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
cheapest_models_for — Cheapest models for a workload
Advertised by the server during the last successful anonymous check.
Advertised read-only

Rank models by monthly cost for a workload. Use a preset (chatbot, rag, coding_agent, research_agent) or give token numbers.

cheapest_models_for input schema
{
  "type": "object",
  "properties": {
    "limit": {
      "type": "number",
      "description": "How many to return (default 5, max 20)"
    },
    "preset": {
      "enum": [
        "chatbot",
        "rag",
        "coding_agent",
        "research_agent"
      ],
      "type": "string",
      "description": "Optional workload preset that fills in token defaults: chatbot, rag, coding_agent, research_agent. Explicit numbers override it."
    },
    "input_tokens": {
      "type": "number",
      "description": "Input tokens per call/step"
    },
    "popular_only": {
      "type": "boolean",
      "description": "Only well-known models (default true)"
    },
    "calls_per_day": {
      "type": "number",
      "description": "Calls (or agent tasks) per day"
    },
    "output_tokens": {
      "type": "number",
      "description": "Output tokens per call/step"
    },
    "cached_percent": {
      "type": "number",
      "description": "Share of input billed at the cached price, 0-100 (default 50 if steps_per_task>1, else 0)"
    },
    "steps_per_task": {
      "type": "number",
      "description": "Model calls per task for multi-step agents (default 1)"
    }
  }
}
cheapest_models_for annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

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
342 ms
95th percentile latency
342 ms

Maintenance history

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

  • · probe · passed · 342 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 agent-cost-hub-mcp https://agentcosthub.com/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 agent-cost-hub-mcp --url https://agentcosthub.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable agent-cost-hub-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "agent-cost-hub-mcp": {
      "url": "https://agentcosthub.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "agent-cost-hub-mcp": {
      "type": "streamableHttp",
      "url": "https://agentcosthub.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start agent-cost-hub-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "agent-cost-hub-mcp": {
      "type": "http",
      "url": "https://agentcosthub.com/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 agent-cost-hub-mcp https://agentcosthub.com/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "agent-cost-hub-mcp": {
      "url": "https://agentcosthub.com/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": {
    "agent-cost-hub-mcp": {
      "serverUrl": "https://agentcosthub.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Agent Cost Hub 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
See all 4,381

Do you run Agent Cost Hub 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