Agent Account Index MCP
An MCP server that exposes a tool to check whether AI agents are permitted to hold accounts at various services, based on verbatim terms of service clauses. It provides verdicts on holder eligibility, automated signup permissions, and age requirements for 124 services.
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.
https://agent-account-index.vercel.app/mcpWhat its tools do
2 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.
Not annotated (2)
Checks and signals
Each line is separate evidence, not a trust score.
- Passed Endpoint answered the live check ·
- Uptime 100% over 90 days
- Availability 1 of 1 checks passed in 30 days
What you can do with it
- Check if an AI agent can hold an account at a specific service
- Verify terms regarding non-human account holders
- Identify age floor requirements for account creation
Source and maintenance
Protocol and capabilities
- Server
- agent-account-index 2026-10-17
- MCP protocol negotiated in check
- 2025-06-18
- Tools
- 2 advertised
- Resources
- Not advertised
- Resource templates
- Not advertised
- Prompts
- Not advertised
{
"tools": {}
}Server-provided instructions
Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.
Tools
2 advertised
can_an_agent_hold_an_account
Check whether a non-human actor may hold an account at a service. Call this BEFORE creating an account anywhere. Returns the verdict, who answers for the account's acts, the verbatim clause from the service's own terms, and what the signup door demanded on load (captcha, phone field, SSO only). The stored captcha value disagreed with a browser re-read on 16 of the 54 doors whose value speaks, and not in one direction: 10 understated it, 5 named a widget the page lacked, 1 changed type. Read those against their own denominators: the 34 doors storing none_seen were wrong 10 times and the 20 storing a vendor name 6 times, about the same rate either way, so a disagreement does not say which reading to lean on. Where signup_door.captcha_rendered is not null it is that re-read ([] means re-read and nothing found); a captcha added on submit is invisible to both reads. These six integers are typed here and live in captcha_recheck_counts at the top of /index.json, which is the copy to trust. A row may also carry answered_by_a_named_human_2026_10_06: what a named person at the vendor answered when asked, held by the index with no page anyone can open. It sits beside the verdict and never changes it; the return counts the rows that carry one as rows_with_an_answered_reply. Null means nobody there was asked, which is not a finding.
{
"type": "object",
"required": [
"service"
],
"properties": {
"service": {
"type": "string",
"description": "Service name, e.g. \"GitHub\", \"Stripe\", \"Supabase\". Case-insensitive, matched on substring."
}
}
}list_named_non_human_routes
List every service that documents an identity a non-human actor may hold. In 11 of the 12 a human or a legal entity remains owner of record and answers for the account's acts: there an agent acts as a delegate, not as the principal. 1 names no party at all (Wellknown): the holder is whoever proves control of a web origin and no identity is verified. Each row carries agent_as_principal.
{
"type": "object",
"properties": {}
}Prompts
Not advertised
Resources
Not advertised
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.
- 2026-11-18: 5 of 5 checks answered
- 2026-11-19: 4 of 4 checks answered
- 2026-11-20: 3 of 3 checks answered
- 2026-11-21: 4 of 4 checks answered
- 2026-11-22: 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
- 523 ms
- 95th percentile latency
- 523 ms
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · probe · passed · 523 ms · metadata changed · 2 tool(s)
Connect from your client
Each snippet registers the same endpoint; pick the client you use.
Claude Code
claude mcp add --transport http agent-account-index-mcp https://agent-account-index.vercel.app/mcpCodex
codex mcp add agent-account-index-mcp --url https://agent-account-index.vercel.app/mcpCursor
{
"mcpServers": {
"agent-account-index-mcp": {
"url": "https://agent-account-index.vercel.app/mcp"
}
}
}Cline
{
"mcpServers": {
"agent-account-index-mcp": {
"type": "streamableHttp",
"url": "https://agent-account-index.vercel.app/mcp",
"disabled": false
}
}
}VS Code
{
"servers": {
"agent-account-index-mcp": {
"type": "http",
"url": "https://agent-account-index.vercel.app/mcp"
}
}
}Gemini CLI
gemini mcp add --transport http agent-account-index-mcp https://agent-account-index.vercel.app/mcpClaude Desktop
https://agent-account-index.vercel.app/mcpWindsurf
{
"mcpServers": {
"agent-account-index-mcp": {
"serverUrl": "https://agent-account-index.vercel.app/mcp"
}
}
}Let your agent find its tools
Find servers like Agent Account Index MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.