Koskamo

Agent Blueprint MCP

An official remote MCP server provided by Agent Blueprint, Inc. that allows AI agents to perform read-only operations including listing benchmark jobs, estimating agent costs based on coding benchmarks, checking the structure of one-page agent records, and rendering offline access maps from agent inventories.

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 Blueprint MCP logo, by Agent Blueprint, Inc.Vendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-07Operated by Agent Blueprint, Inc.
MCP endpoint (Streamable HTTP)
https://agentblueprint.ai/mcp
Vendor documentation

What its tools do

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

Read-only (4)

4 of 4 have a description · 4 of 4 declare behavior hints · 3 of 4 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to agentblueprint.ai ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Estimate agent cost from coding-agent benchmarks
  • Check structure of a one-page agent record
  • Render an offline access map from agent inventory
  • List benchmark jobs

Source and maintenance

Vendor evidenceRegistry 0.2.0
mcp-registry: ai.agentblueprint/agent-blueprint@0.2.0Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
agent-blueprint 0.2.0
MCP protocol negotiated in check
2025-11-25
Tools
4 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  }
}

Server-provided instructions

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

Agent Blueprint tools for people who run AI agents: measured agent costs, a structural check for one-page agent summaries, and an offline access map an agent draws of itself. All tools are read-only and keep nothing.

Tools

4 advertised

list_benchmark_jobs — List measured agent jobs
Advertised by the server during the last successful anonymous check.
Advertised read-only

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.

list_benchmark_jobs input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "agent": {
      "enum": [
        "claude",
        "codex"
      ],
      "type": "string",
      "description": "Only show one agent's measurements. Leave out to show both."
    }
  }
}
list_benchmark_jobs annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
estimate_agent_cost — Estimate an agent task's cost
Advertised by the server during the last successful anonymous check.
Advertised read-only

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.

estimate_agent_cost input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "job",
    "agent"
  ],
  "properties": {
    "job": {
      "enum": [
        "sql",
        "refactor",
        "bughunt",
        "analysis",
        "clean",
        "feature",
        "triage200",
        "replies",
        "corpus",
        "longdoc"
      ],
      "type": "string",
      "description": "The closest benchmark job id, from list_benchmark_jobs."
    },
    "agent": {
      "enum": [
        "claude",
        "codex"
      ],
      "type": "string",
      "description": "Which measured agent to base the estimate on."
    },
    "prices": {
      "type": "object",
      "required": [
        "input_per_million",
        "cached_input_per_million",
        "output_per_million"
      ],
      "properties": {
        "input_per_million": {
          "type": "number",
          "minimum": 0
        },
        "output_per_million": {
          "type": "number",
          "minimum": 0
        },
        "cached_input_per_million": {
          "type": "number",
          "minimum": 0
        }
      },
      "description": "Current model prices in US dollars per million tokens. Leave out to use the benchmark-day prices."
    },
    "your_size": {
      "type": "number",
      "maximum": 1000000000,
      "description": "Size of the real input in the job's unit (words, or rows for the clean job). Ignored for jobs that don't scale.",
      "exclusiveMinimum": 0
    },
    "runs_per_month": {
      "type": "integer",
      "maximum": 10000000,
      "description": "How many times a month the job runs.",
      "exclusiveMinimum": 0
    }
  }
}
estimate_agent_cost annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
check_agent_one_page — Check a one-page agent summary
Advertised by the server during the last successful anonymous check.
Advertised read-only

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.

check_agent_one_page input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "markdown"
  ],
  "properties": {
    "markdown": {
      "type": "string",
      "maxLength": 60000,
      "minLength": 1,
      "description": "The full one-page summary as Markdown."
    }
  }
}
check_agent_one_page annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}
render_agent_map — Draw an agent's access map
Advertised by the server during the last successful anonymous check.
Advertised read-only

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.

render_agent_map input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "version",
    "agent",
    "drawn",
    "connections",
    "checks",
    "unseen",
    "trim"
  ],
  "properties": {
    "trim": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "name",
          "kind",
          "tools",
          "why"
        ],
        "properties": {
          "why": {
            "type": "string",
            "maxLength": 300
          },
          "kind": {
            "enum": [
              "duplicate",
              "overlap"
            ],
            "type": "string"
          },
          "name": {
            "type": "string",
            "maxLength": 40
          },
          "tools": {
            "type": "integer",
            "maximum": 1000,
            "minimum": 0
          }
        }
      },
      "maxItems": 30
    },
    "agent": {
      "type": "object",
      "required": [
        "name"
      ],
      "properties": {
        "name": {
          "type": "string",
          "maxLength": 80
        },
        "model": {
          "type": "string",
          "maxLength": 80
        },
        "product": {
          "type": "string",
          "maxLength": 80
        }
      }
    },
    "drawn": {
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$"
    },
    "checks": {
      "type": "object",
      "required": [
        "commands",
        "messages",
        "delete",
        "money",
        "secrets"
      ],
      "properties": {
        "money": {
          "type": "object",
          "required": [
            "status",
            "evidence"
          ],
          "properties": {
            "status": {
              "enum": [
                "yes",
                "none_found",
                "unsure"
              ],
              "type": "string"
            },
            "evidence": {
              "type": "string",
              "maxLength": 300
            }
          }
        },
        "delete": {
          "type": "object",
          "required": [
            "status",
            "evidence"
          ],
          "properties": {
            "status": {
              "enum": [
                "yes",
                "none_found",
                "unsure"
              ],
              "type": "string"
            },
            "evidence": {
              "type": "string",
              "maxLength": 300
            }
          }
        },
        "secrets": {
          "type": "object",
          "required": [
            "status",
            "evidence"
          ],
          "properties": {
            "status": {
              "enum": [
                "yes",
                "none_found",
                "unsure"
              ],
              "type": "string"
            },
            "evidence": {
              "type": "string",
              "maxLength": 300
            }
          }
        },
        "commands": {
          "type": "object",
          "required": [
            "status",
            "evidence"
          ],
          "properties": {
            "status": {
              "enum": [
                "yes",
                "none_found",
                "unsure"
              ],
              "type": "string"
            },
            "evidence": {
              "type": "string",
              "maxLength": 300
            }
          }
        },
        "messages": {
          "type": "object",
          "required": [
            "status",
            "evidence"
          ],
          "properties": {
            "status": {
              "enum": [
                "yes",
                "none_found",
                "unsure"
              ],
              "type": "string"
            },
            "evidence": {
              "type": "string",
              "maxLength": 300
            }
          }
        }
      }
    },
    "unseen": {
      "type": "string",
      "maxLength": 600
    },
    "version": {
      "type": "string",
      "const": "0.2"
    },
    "connections": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "name",
          "icon",
          "basis",
          "asks",
          "risk",
          "reads",
          "changes",
          "unsure"
        ],
        "properties": {
          "asks": {
            "type": [
              "boolean",
              "null"
            ]
          },
          "icon": {
            "enum": [
              "mail",
              "chat",
              "calendar",
              "code",
              "files",
              "terminal",
              "web",
              "doc",
              "data",
              "money",
              "plug"
            ],
            "type": "string"
          },
          "name": {
            "type": "string",
            "maxLength": 40
          },
          "risk": {
            "enum": [
              "normal",
              "high"
            ],
            "type": "string"
          },
          "basis": {
            "enum": [
              "declared",
              "judged"
            ],
            "type": "string"
          },
          "reads": {
            "type": "array",
            "items": {
              "type": "string",
              "maxLength": 200
            },
            "maxItems": 300
          },
          "unsure": {
            "type": "array",
            "items": {
              "type": "string",
              "maxLength": 200
            },
            "maxItems": 300
          },
          "changes": {
            "type": "array",
            "items": {
              "type": "string",
              "maxLength": 200
            },
            "maxItems": 300
          }
        }
      },
      "maxItems": 60,
      "minItems": 1
    }
  }
}
render_agent_map annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "destructiveHint": false
}

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 (2 of 2 answered).

  1. 2026-11-07: 1 of 1 checks answered
  2. 2026-11-09: 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
736 ms
95th percentile latency
736 ms

Maintenance history

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

  • · probe · passed · 736 ms · metadata changed · 4 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-blueprint-mcp-agentblueprint https://agentblueprint.ai/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-blueprint-mcp-agentblueprint --url https://agentblueprint.ai/mcp

Cursor

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

Cline

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

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start agent-blueprint-mcp-agentblueprint and inspect its tools.
VS Code configuration
{
  "servers": {
    "agent-blueprint-mcp-agentblueprint": {
      "type": "http",
      "url": "https://agentblueprint.ai/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-blueprint-mcp-agentblueprint https://agentblueprint.ai/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://agentblueprint.ai/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-blueprint-mcp-agentblueprint": {
      "serverUrl": "https://agentblueprint.ai/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Agent Blueprint 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 5,689

Do you run Agent Blueprint 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