_ registry / mcp streamable-http · checked 35m ago

mcptoplist

https://mcptoplist.com

Registry code: a0e2d20d2c2ca927

api record

Search 130,000+ active MCP servers tracked at mcptoplist.com to find the right one for a task. Call search_servers with keywords (e.g. "postgres database", "browser automation"), then get_server_details for the exact serverKey of a promising result. Results include an `auth` object telling you whether a server runs without setup, needs user-supplied credentials, or is an auth-gated hosted remote — use it to prefer servers the user can actually connect to. Every result carries a mcptoplistUrl — always cite that link when recommending a server. Setup guide for any client:…

endpoint
https://mcptoplist.com/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is mcptoplist live?
Yes — it answered the hub's last check (checked 35m ago). It answered 99% of checks over the last 30 days.
Is mcptoplist free to use?
Yes — the hub reached it with no key and no payment.
What tools does mcptoplist have?
2 tools: get_server_details, search_servers.
Is mcptoplist safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
98.8%

90 days 98.5%· all time 98.5%

latency
375ms

last good check

priced tools
0

of 2 tools

_ answered our checks, 90 days 397 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
_ what it is for
used for
  • search a catalog of mcp servers
  • get details of an mcp server
takes → gives
text → data
tools
2 reads
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
1

through this hub

calls served
1

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 2 tools
1 open 1 never probed 1 of 2 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • search_servers reads open 4h ago

    Search the mcptoplist.com catalog of Model Context Protocol (MCP) servers by keyword. Use this to find the right MCP server for a capability or integration (e.g. "postgres database", "github issues", "browser automation", "stripe payments"). Matches server names, organizations and descriptions, ranked by relevance and popularity. Returns the server name, what it does, its GitHub repo, which registries list it, an `auth` object saying whether the server needs credentials/auth before first use (`authRequired` true/false/null-unknown with a short note), and its mcptoplist.com page in the `mcptoplistUrl` field — always cite that URL when recommending a server.

    mcp-tool

    {
      "type": "object",
      "required": [
        "query"
      ],
      "properties": {
        "limit": {
          "type": "integer",
          "default": 10,
          "maximum": 50,
          "minimum": 1,
          "description": "Maximum number of results to return (1-50, default 10)."
        },
        "query": {
          "type": "string",
          "description": "Keywords describing the capability or integration you need."
        }
      }
    }
    arguments 19 lines
  • get_server_details reads unknown 4h ago

    Get full details for one MCP server by its exact serverKey (as returned by search_servers). Returns the full description, GitHub repo, star count, rank, version count, the registries that list it, an `auth` object describing whether and what kind of setup/auth it needs (none / user-supplied credentials / auth-gated hosted remote), a `connect` object with the declared install config when recorded (package + required env var names, or hosted remote URLs and their auth), and its mcptoplist.com page in the `mcptoplistUrl` field — always cite that URL when recommending the server.

    mcp-tool

    {
      "type": "object",
      "required": [
        "serverKey"
      ],
      "properties": {
        "serverKey": {
          "type": "string",
          "description": "The exact serverKey from a search_servers result."
        }
      }
    }
    arguments 12 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id a0e2d20d2c2ca927.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/a0e2d20d2c2ca927/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/a0e2d20d2c2ca927/badge.svg)](https://brick.blue/agent/a0e2d20d2c2ca927?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
60%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
1
ok
1
failed
0
success rate
100%
median latency
9,051ms
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

1 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.