Koskamo

Agent Access Index MCP

An MCP server that determines if an AI agent can fetch a specific URL, on what terms, and at what price. It checks robots.txt, well-known files, and live responses to provide verdicts like allowed, charged, or blocked without storing content or training models.

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 Access Index MCP logo, by AgentwaresCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-07Published by Agentwares
MCP endpoint (Streamable HTTP)
https://agentwares-access-index.vercel.app/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 · 1 of 1 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Determine if an AI agent may fetch a URL
  • Check access terms and pricing for a URL
  • List AI crawler tokens for robots.txt auditing

Source and maintenance

Community listingRegistry 0.1.0
mcp-registry: io.github.agentwares/agent-access-index@0.1.0Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
agent-access-index 0.1.0
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
  },
  "logging": {}
}

Server-provided instructions

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

Ask this server why a fetch was refused and what to do about it. `access_check_url` is the main tool: it reads the origin's robots.txt, its AI-preference directives, any licence it links, and the live response to an honestly-identified request, and returns a verdict with the evidence behind it. The verdict that matters is `allowed_if_identified`: the site's written policy permits the fetch and the refusal came from bot management, which means identifying and signing as a named crawler is a documented route to the content rather than a guess. Every answer carries a `next` field, `{ what, url, why }` or null: when a tool we publish today closes the gap the verdict names — the signing library for an `allowed_if_identified` URL — `next` names it; on every other verdict it is null. This server never evades anything and never impersonates another operator's crawler. The per-agent answers come from what the origin declared, not from testing with a borrowed user-agent. If robots.txt disallows this index, it says so and does not fetch the page.

Tools

3 advertised

access_check_url — Check whether an agent may fetch a URL
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Says whether an AI agent may fetch a URL, on what terms, and at what price. Reads robots.txt for a generic agent and for every AI user-agent the operators document, the Content-signal and Content-Usage directives, any RSL licence the origin links, and the live response to an honestly-identified request. Verdicts: `allowed` (it served us), `allowed_if_identified` (the written policy permits this but bot management refused an anonymous request — signing as a named crawler is the documented route), `charged` (there is a price, quoted where the rail will show one), `blocked` (the site disallows the agents that would want this, with nothing to buy), and `unknown` (the origin did not answer, or the URL is not there). Never evades: no CAPTCHA solving, no proxies, no spoofed user-agents. Refusals come back as findings with the evidence attached.

access_check_url input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "Absolute http(s) URL of the page to check, e.g. https://example.com/article"
    },
    "skipWellKnown": {
      "type": "boolean",
      "description": "When true, the five well-known probes are skipped; faster, and those files are almost always absent"
    },
    "includeEvidence": {
      "type": "boolean",
      "description": "When true, the answer includes every request made, with status and headers (default false: it is large)"
    }
  },
  "additionalProperties": false
}
access_check_url annotations
{
  "title": "Check whether an agent may fetch a URL",
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
access_explain_verdicts — What the verdicts mean
Advertised by the server during the last successful anonymous check.
Advertised read-only

Returns the five verdicts access_check_url can give, what each one means for an agent that has just been refused, and the next move for each, plus what each confidence level rests on. Free, makes no network request, and returns the same answer every time: it is the key to reading access_check_url results.

access_explain_verdicts input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {},
  "additionalProperties": false
}
access_explain_verdicts annotations
{
  "title": "What the verdicts mean",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
access_list_agents — AI user-agents this index reports on
Advertised by the server during the last successful anonymous check.
Advertised read-only

Returns the AI crawler tokens this index reads robots.txt rules for — only tokens their operators document — plus the widely-written tokens that no operator sends, which make a robots rule unenforceable, and the list of verdict names. Useful when writing or auditing a robots.txt.

access_list_agents input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {},
  "additionalProperties": false
}
access_list_agents annotations
{
  "title": "AI user-agents this index reports on",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

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
597 ms
95th percentile latency
597 ms

Maintenance history

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

  • · probe · passed · 597 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-access-index-mcp https://agentwares-access-index.vercel.app/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-access-index-mcp --url https://agentwares-access-index.vercel.app/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable agent-access-index-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "agent-access-index-mcp": {
      "url": "https://agentwares-access-index.vercel.app/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "agent-access-index-mcp": {
      "type": "streamableHttp",
      "url": "https://agentwares-access-index.vercel.app/mcp",
      "disabled": false
    }
  }
}

VS Code

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

Let your agent find its tools

Find servers like Agent Access Index 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 8,317