# Agent Blueprint (remote · agentblueprint.ai)

Measured agent costs, a one-page agent summary check, and an offline access map. No sign-in.

- Trust score: 72/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `agentblueprint.ai`: 72/100 (this document), [markdown](https://verifymcp.io/servers/ai-agentblueprint-agent-blueprint/agentblueprint.md), [page](https://verifymcp.io/servers/ai-agentblueprint-agent-blueprint/agentblueprint)

## Channel facts

- Endpoint: `https://agentblueprint.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.0`

## 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**: 80/100
  - 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.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 66/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 664 tokens (~166/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 7/100
  - Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 83/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 50% 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 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Agent Blueprint MCP server?

Agent Blueprint is a hosted endpoint at https://agentblueprint.ai/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 ai-agentblueprint-agent-blueprint 'https://agentblueprint.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-agentblueprint-agent-blueprint": {
      "url": "https://agentblueprint.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-agentblueprint-agent-blueprint": {
      "type": "http",
      "url": "https://agentblueprint.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-agentblueprint-agent-blueprint]
url = "https://agentblueprint.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-agentblueprint-agent-blueprint": {
      "type": "remote",
      "url": "https://agentblueprint.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-agentblueprint-agent-blueprint --url 'https://agentblueprint.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-agentblueprint-agent-blueprint:
    url: "https://agentblueprint.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-agentblueprint-agent-blueprint": {
      "Transport": "http",
      "Url": "https://agentblueprint.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-agentblueprint-agent-blueprint -t streamable-http -u 'https://agentblueprint.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-agentblueprint-agent-blueprint": {
      "type": "http",
      "url": "https://agentblueprint.ai/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 72, +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.

### 2026-11-04 (score 71, 0)

- [security] Tool “check_agent_one_page” rewrote its description, which is the text the model reads
- [functional improvement] Stability: unverified → 0.03

### 2026-11-03 (score 71)

First indexed and scored.

## MCP tools (4)

### `list_benchmark_jobs` (~107 tokens)

List measured agent jobs

Lists the ten everyday jobs in Agent Blueprint's measured agent cost benchmark (2 November 2026): what each job was, how big its input was, and the typical and worst-case tokens and dollar cost measured over five runs each on Claude Code and Codex. Use it to find the benchmark job closest to a task someone wants an agent to do, before estimating that task's cost.

Input parameters:

- `agent` (string): Only show one agent's measurements. Leave out to show both.

### `estimate_agent_cost` (~223 tokens)

Estimate an agent task's cost

Estimates the tokens and dollar cost of an AI agent task from the measured benchmark job closest to it. For jobs where cost grows with how much the agent reads, give the size of the real input and it scales the reading part while keeping the agent's fixed overhead. Returns a typical and a budget (worst-case) figure per run and, if runs per month are given, per month. Uses the benchmark-day prices unless current prices are passed. The result is an estimate from small test jobs, not a quote.

Input parameters:

- `agent` (string, required): Which measured agent to base the estimate on.
- `job` (string, required): The closest benchmark job id, from list_benchmark_jobs.
- `prices` (object): Current model prices in US dollars per million tokens. Leave out to use the benchmark-day prices.
- `runs_per_month` (integer): How many times a month the job runs.
- `your_size` (number): Size of the real input in the job's unit (words, or rows for the clean job). Ignored for jobs that don't scale.

### `check_agent_one_page` (~126 tokens)

Check a one-page agent summary

Checks the structure of a one-page agent summary written from Agent Blueprint's template (https://agentblueprint.ai/agent-one-page-template): the summary and all seven numbered sections present and in order, a stage line, every rule ending in "Enforced by:" or "Not enforced:", every Open item naming who decides, no template placeholders left, and length within one page. It checks shape only, not whether the answers are right. The text is checked and returned findings only; it is not stored.

Input parameters:

- `markdown` (string, required): The full one-page summary as Markdown.

### `render_agent_map` (~162 tokens)

Draw an agent's access map

Turns an agent's own inventory of its connections into Agent Blueprint's one-page access map: a single offline HTML page showing what the agent can read and change, who has to approve, its riskiest powers, and what could be trimmed. The agent supplies the inventory from its own tool list; this tool only draws it. Returns the HTML for the person to save, such as my-agent-blueprint.html. The inventory is not stored. The field guide is at https://agentblueprint.ai/draw.md.

Input parameters:

- `agent` (object, required)
- `checks` (object, required)
- `connections` (array, required)
- `drawn` (string, required)
- `trim` (array, required)
- `unseen` (string, required)
- `version` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-agentblueprint-agent-blueprint/agentblueprint#diagnostics

## Score history

- 2026-11-05: 72
- 2026-11-04: 71
- 2026-11-03: 71

## Common questions

### What is the Agent Blueprint MCP server?

Agent Blueprint is an MCP server listed in the public MCP registry as ai.agentblueprint/agent-blueprint. Measured agent costs, a one-page agent summary check, and an offline access map. No sign-in. This page covers its hosted endpoint (https://agentblueprint.ai/mcp).

### Is the Agent Blueprint MCP server safe to use?

Agent Blueprint scores 72 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 Blueprint MCP server expose?

Agent Blueprint exposes 4 tools: list_benchmark_jobs, estimate_agent_cost, check_agent_one_page, render_agent_map. Their descriptions and schemas cost roughly 618 tokens of context every time the server is loaded.

### Does the Agent Blueprint MCP server require authentication?

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

### Is the Agent Blueprint MCP server still maintained?

Agent Blueprint 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://agentblueprint.ai/mcp
- Repository: https://github.com/agent-blueprint/agent-blueprint-website
- Website: https://agentblueprint.ai/agents
- Changelog RSS feed: https://verifymcp.io/servers/ai-agentblueprint-agent-blueprint/agentblueprint.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-agentblueprint-agent-blueprint/agentblueprint.json
- HTML version of this page: https://verifymcp.io/servers/ai-agentblueprint-agent-blueprint/agentblueprint