Koskamo

Agent Surface MCP

An official MCP server provided by Agent Surface that allows AI agents to search, list, and read the Agent Surface documentation on making websites and apps agent-ready. It supports operations like search, list_pages, and get_page to retrieve documentation content in Markdown format.

Visit Agent Surface

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 Surface MCP logo, by Agent SurfaceVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-07Operated by Agent Surface
MCP endpoint (Streamable HTTP)
https://agentsurface.dev/mcp
Vendor documentation

What its tools do

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

Read-only (3)

3 of 3 have a description · 3 of 3 declare behavior hints · 3 of 3 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 agentsurface.dev ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Search the Agent Surface documentation for agent-ready best practices
  • List available documentation pages via the MCP server
  • Retrieve specific documentation pages in Markdown format

Source and maintenance

Vendor evidenceRegistry 2.3.0
mcp-registry: dev.agentsurface/docs@2.3.0Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
agentsurface-docs 2.3.0
MCP protocol negotiated in check
2025-11-25
Tools
3 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.

Search first to find relevant documentation, or list_pages to browse. Then get_page with a canonical URL to read the full Markdown. All tools are public and read-only. Search returns at most 20 pages; narrow query or section when has_more is true.

Tools

3 advertised

search — Search documentation
Advertised by the server during the last successful anonymous check.
Advertised read-only

Use when you know the topic but need authoritative pages. Searches titles, descriptions, headings and body; deduplicates chunks into pages in Fumadocs full-text relevance order (ZBSearch). Rank is a position, not confidence. Read a result with get_page; narrow query or section if has_more is true.

search input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 5,
      "maximum": 20,
      "minimum": 1,
      "description": "Maximum pages to return, from 1 to 20; defaults to 5."
    },
    "query": {
      "type": "string",
      "maxLength": 500,
      "minLength": 2,
      "description": "Keywords to find in documentation titles, descriptions, headings and body; 2 to 500 characters."
    },
    "section": {
      "type": "string",
      "pattern": "^[a-z0-9-]+$",
      "description": "Optional top-level docs section, for example discovery, mcp-servers or retrievability. Unknown sections return no matches."
    }
  }
}
search output schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "results",
    "has_more",
    "ranking"
  ],
  "properties": {
    "ranking": {
      "type": "string",
      "description": "Explanation of the relevance ordering and rank semantics."
    },
    "results": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "id",
          "title",
          "description",
          "url",
          "slug",
          "snippet",
          "rank"
        ],
        "properties": {
          "id": {
            "type": "string",
            "description": "Stable documentation path, independent of rank."
          },
          "url": {
            "type": "string",
            "format": "uri",
            "description": "Canonical source URL; pass this to get_page."
          },
          "rank": {
            "type": "integer",
            "maximum": 20,
            "minimum": 1,
            "description": "1-based position within this result set, lower is earlier; not confidence and not comparable across queries."
          },
          "slug": {
            "type": "string",
            "description": "Slash-separated docs slug for /api/md; index identifies the docs home."
          },
          "title": {
            "type": "string",
            "description": "Published page title."
          },
          "snippet": {
            "type": "string",
            "maxLength": 600,
            "description": "Matching body or heading excerpt, at most 600 characters."
          },
          "updated_at": {
            "type": "string",
            "description": "Content revision time, or last verification date where a revision time is unavailable."
          },
          "description": {
            "type": "string",
            "description": "Published page summary."
          }
        },
        "additionalProperties": false
      },
      "maxItems": 20,
      "description": "Distinct matching documentation pages, bounded by the caller limit."
    },
    "has_more": {
      "type": "boolean",
      "description": "More matching pages exist beyond this limit. Narrow query or section, increase limit up to 20, or browse list_pages."
    }
  },
  "additionalProperties": false
}
search annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
list_pages — Browse documentation
Advertised by the server during the last successful anonymous check.
Advertised read-only

Use when you do not know the topic keywords. Browse page identities and URLs, optionally within a section; then get_page to read one. Pages are sorted by URL. Use offset plus limit for the next slice of this static index.

list_pages input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "limit": {
      "type": "integer",
      "default": 30,
      "maximum": 100,
      "minimum": 1,
      "description": "Maximum pages, default 30, maximum 100."
    },
    "offset": {
      "type": "integer",
      "default": 0,
      "maximum": 9007199254740991,
      "minimum": 0,
      "description": "Zero-based index offset; add the previous limit for the next slice. Restart after a deployment."
    },
    "section": {
      "type": "string",
      "pattern": "^[a-z0-9-]+$",
      "description": "Optional top-level docs section, for example discovery, mcp-servers or retrievability. Unknown sections return no matches."
    }
  }
}
list_pages output schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "pages",
    "has_more",
    "next_offset"
  ],
  "properties": {
    "pages": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "id",
          "title",
          "description",
          "url",
          "slug"
        ],
        "properties": {
          "id": {
            "type": "string",
            "description": "Stable documentation path, independent of rank."
          },
          "url": {
            "type": "string",
            "format": "uri",
            "description": "Canonical source URL; pass this to get_page."
          },
          "slug": {
            "type": "string",
            "description": "Slash-separated docs slug for /api/md; index identifies the docs home."
          },
          "title": {
            "type": "string",
            "description": "Published page title."
          },
          "updated_at": {
            "type": "string",
            "description": "Content revision time, or last verification date where a revision time is unavailable."
          },
          "description": {
            "type": "string",
            "description": "Published page summary."
          }
        },
        "additionalProperties": false
      }
    },
    "has_more": {
      "type": "boolean"
    },
    "next_offset": {
      "type": [
        "number",
        "null"
      ]
    }
  },
  "additionalProperties": false
}
list_pages annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_page — Read a documentation page
Advertised by the server during the last successful anonymous check.
Advertised read-only

Use after search or list_pages to read the authoritative full Markdown of one page, including canonical URL and freshness metadata. This does not fetch external websites. On PAGE_NOT_FOUND, search again or browse the public index.

get_page input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "Canonical Agent Surface docs URL or path returned by search or list_pages, for example /docs/discovery/llms-txt."
    }
  }
}
get_page output schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "id",
    "url",
    "markdown"
  ],
  "properties": {
    "id": {
      "type": "string"
    },
    "url": {
      "type": "string"
    },
    "markdown": {
      "type": "string"
    },
    "updated_at": {
      "type": "string"
    }
  },
  "additionalProperties": false
}
get_page annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "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
477 ms
95th percentile latency
477 ms

Maintenance history

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

  • · probe · passed · 477 ms · metadata changed · 3 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-surface-mcp https://agentsurface.dev/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-surface-mcp --url https://agentsurface.dev/mcp

Cursor

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

Cline

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

VS Code

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

Let your agent find its tools

Find servers like Agent Surface 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 1,437

Do you run Agent Surface 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