# Agent Cost Hub (remote · agentcosthub.com)

LLM API prices and AI agent cost estimates, verified daily. Read-only cost lookup tools.

- Trust score: 69/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `agentcosthub.com`: 69/100 (this document), [markdown](https://verifymcp.io/servers/com-agentcosthub-agent-cost-hub/agentcosthub.md), [page](https://verifymcp.io/servers/com-agentcosthub-agent-cost-hub/agentcosthub)

## Channel facts

- Endpoint: `https://agentcosthub.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 62/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 767 tokens (~153/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 96/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 88% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the Agent Cost Hub MCP server?

Agent Cost Hub is a hosted endpoint at https://agentcosthub.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-agentcosthub-agent-cost-hub 'https://agentcosthub.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-agentcosthub-agent-cost-hub": {
      "url": "https://agentcosthub.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-agentcosthub-agent-cost-hub": {
      "type": "http",
      "url": "https://agentcosthub.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-agentcosthub-agent-cost-hub]
url = "https://agentcosthub.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-agentcosthub-agent-cost-hub": {
      "type": "remote",
      "url": "https://agentcosthub.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-agentcosthub-agent-cost-hub --url 'https://agentcosthub.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-agentcosthub-agent-cost-hub:
    url: "https://agentcosthub.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-agentcosthub-agent-cost-hub": {
      "Transport": "http",
      "Url": "https://agentcosthub.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-agentcosthub-agent-cost-hub -t streamable-http -u 'https://agentcosthub.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-agentcosthub-agent-cost-hub": {
      "type": "http",
      "url": "https://agentcosthub.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 69, +1)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-11-04 (score 68, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-11-03 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 67, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional improvement] Stability: unverified → 0.03

### 2026-11-01 (score 67)

First indexed and scored.

## MCP tools (5)

### `list_models` (~66 tokens)

List models

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

Input parameters:

- `popular_only` (boolean)
- `provider` (string): e.g. openai, anthropic, google
- `search` (string)

### `get_model_price` (~60 tokens)

Get model price

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

Input parameters:

- `model` (string, required): Model id like anthropic/claude-sonnet-5.5, or a name

### `estimate_cost` (~234 tokens)

Estimate agent cost

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.

Input parameters:

- `cached_percent` (number): Share of input billed at the cached price, 0-100 (default 50 if steps_per_task>1, else 0)
- `calls_per_day` (number): Calls (or agent tasks) per day
- `input_tokens` (number): Input tokens per call/step
- `model` (string, required): Model id like anthropic/claude-sonnet-5.5, or a name like "Grok 4.7"
- `output_tokens` (number): Output tokens per call/step
- `preset` (string): Optional workload preset that fills in token defaults: chatbot, rag, coding_agent, research_agent. Explicit numbers override it.
- `steps_per_task` (number): Model calls per task for multi-step agents (default 1)

### `compare_models` (~167 tokens)

Compare models

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

Input parameters:

- `cached_percent` (number): Share of input billed at the cached price, 0-100 (default 50 if steps_per_task>1, else 0)
- `calls_per_day` (number): Calls (or agent tasks) per day
- `input_tokens` (number): Input tokens per call/step
- `models` (array, required)
- `output_tokens` (number): Output tokens per call/step
- `preset` (string): Optional workload preset that fills in token defaults: chatbot, rag, coding_agent, research_agent. Explicit numbers override it.
- `steps_per_task` (number): Model calls per task for multi-step agents (default 1)

### `cheapest_models_for` (~203 tokens)

Cheapest models for a workload

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

Input parameters:

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

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-agentcosthub-agent-cost-hub/agentcosthub#diagnostics

## Score history

- 2026-11-05: 69
- 2026-11-04: 68
- 2026-11-03: 68
- 2026-11-02: 67
- 2026-11-01: 67

## Common questions

### What is the Agent Cost Hub MCP server?

Agent Cost Hub is an MCP server listed in the public MCP registry as com.agentcosthub/agent-cost-hub. LLM API prices and AI agent cost estimates, verified daily. Read-only cost lookup tools. This page covers its hosted endpoint (https://agentcosthub.com/mcp).

### Is the Agent Cost Hub MCP server safe to use?

Agent Cost Hub scores 69 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Agent Cost Hub MCP server expose?

Agent Cost Hub exposes 5 tools: list_models, get_model_price, estimate_cost, compare_models, cheapest_models_for. Their descriptions and schemas cost roughly 730 tokens of context every time the server is loaded.

### Does the Agent Cost Hub MCP server require authentication?

No. We connected to Agent Cost Hub without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Agent Cost Hub MCP server still maintained?

Agent Cost Hub is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://agentcosthub.com/mcp
- Repository: https://github.com/agentcosthub/agent-cost-hub-mcp
- Website: https://agentcosthub.com/mcp/
- Changelog RSS feed: https://verifymcp.io/servers/com-agentcosthub-agent-cost-hub/agentcosthub.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-agentcosthub-agent-cost-hub/agentcosthub.json
- HTML version of this page: https://verifymcp.io/servers/com-agentcosthub-agent-cost-hub/agentcosthub