# AgentCost MCP Server

> Use this tool when you need to optimize AI model spending and manage budgets effectively. The AgentCost MCP Server provides real-time pricing and cost estimation, enabling agents to compare costs across providers and select the most cost-effective models. It takes in AI model and task specifications as input and outputs optimized cost estimates and budget recommendations.

Canonical page: https://skillsregistry.net/skills/oneagentlabs-agentcost-mcp  
JSON: https://api.skillsregistry.net/v1/skills/oneagentlabs-agentcost-mcp

## Description

Provides real-time AI model pricing, cost estimation, and budget management tools to help agents understand and optimize their spending. It enables agents to compare costs across multiple providers and select the most cost-effective models for specific tasks.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** productivity
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/f78n4mvecb)
- **Repository:** <https://github.com/oneagentlabs/agentcost-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "oneagentlabs-agentcost-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/oneagentlabs-agentcost-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/oneagentlabs-agentcost-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt