Find and evaluate MCP servers: search the independent MCP Yellow Pages directory.
Maintained by@MCPYellowPages(verified)Also a maintainer?
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Step 1 of the MCPYP selection funnel (broad search). Returns a broad pool of candidate servers for a task (default 20, paged with offset) plus the total match count. Use this first to see the shape of the pool, then narrow with refine. Pass the same journey_id across explore, refine, and pick so the journey is logged as one funnel.
What the MCP should do
Pool size, default 20, max 100
Page offset into the ranked pool
Optional client-chosen id linking this journey's steps
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http mcpyp https://api.mcpyp.com/mcp
Step 1 of the MCPYP selection funnel (broad search). Returns a broad pool of candidate servers for a task (default 20, paged with offset) plus the total match count. Use this first to see the shape of the pool, then narrow with refine. Pass the same journey_id across explore, refine, and pick so the journey is logged as one funnel.
| Argument | Type | Description |
|---|---|---|
| limit | integer | Pool size, default 20, max 100 |
| query* | string | What the MCP should do |
| offset | integer | Page offset into the ranked pool |
| journey_id | string | Optional client-chosen id linking this journey's steps |
{
"type": "object",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"default": 20,
"description": "Pool size, default 20, max 100"
},
"query": {
"type": "string",
"description": "What the MCP should do"
},
"offset": {
"type": "integer",
"default": 0,
"description": "Page offset into the ranked pool"
},
"journey_id": {
"type": "string",
"description": "Optional client-chosen id linking this journey's steps"
}
}
}Search the MCP Yellow Pages measured catalog. Start here to discover MCP servers for a task. Returns servers ranked by content match, then by independently measured quality (liveness, deep-test results, tool counts). Every result was actually probed by MCPYP; requires_key tells you whether the server needs a publisher API key before use.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| query* | string | What the MCP should do, e.g. 'send email', 'stock prices', 'github issues' |
{
"type": "object",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"default": 10
},
"query": {
"type": "string",
"description": "What the MCP should do, e.g. 'send email', 'stock prices', 'github issues'"
}
}
}Get a ready-to-paste client configuration for one MCP server. If the server requires a publisher API key, the config contains a placeholder plus where to obtain the key; MCPYP never issues or stores keys. Pass the same journey_id as the pick step so the funnel conversion is logged.
| Argument | Type | Description |
|---|---|---|
| name* | string | Server name or slug from find_mcp results |
| journey_id | string | Same journey_id as the pick step |
{
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"description": "Server name or slug from find_mcp results"
},
"journey_id": {
"type": "string",
"description": "Same journey_id as the pick step"
}
}
}Get the full measured profile of one MCP server: description, measured tool list with parameters, liveness and deep-test outcomes, endpoint region. Use after find_mcp to inspect a candidate before connecting.
| Argument | Type | Description |
|---|---|---|
| name* | string | Server name or slug from find_mcp results |
{
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"description": "Server name or slug from find_mcp results"
}
}
}Step 3 of the MCPYP selection funnel (final selection). Commits to exactly ONE server: either the top-ranked server for a further-improved query, or the named server from the refine step. Keep improving the query: each step's query should be sharper than the last, so the journey shows how the choice narrowed. After pick, call get_config to connect. This is the funnel's conversion point.
| Argument | Type | Description |
|---|---|---|
| name | string | Server name or slug from the refine step, when committing to a specific server |
| query | string | Task query, when picking the top-ranked server |
| journey_id | string | Same journey_id as the earlier steps |
{
"type": "object",
"required": [],
"properties": {
"name": {
"type": "string",
"description": "Server name or slug from the refine step, when committing to a specific server"
},
"query": {
"type": "string",
"description": "Task query, when picking the top-ranked server"
},
"journey_id": {
"type": "string",
"description": "Same journey_id as the earlier steps"
}
}
}Step 2 of the MCPYP selection funnel (refined search). Narrows a task to exactly 5 candidates. IMPORTANT: improve the query at each step - use what explore returned (candidate names, tool names, categories) to write a sharper, more specific query here than the explore query. Optionally constrain to servers that need no publisher key (no_key_required). Call after explore, then commit with pick.
| Argument | Type | Description |
|---|---|---|
| query* | string | What the MCP should do, refined from explore |
| journey_id | string | Same journey_id as the explore step |
| no_key_required | boolean | Only servers usable without a publisher API key |
{
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"description": "What the MCP should do, refined from explore"
},
"journey_id": {
"type": "string",
"description": "Same journey_id as the explore step"
},
"no_key_required": {
"type": "boolean",
"default": false,
"description": "Only servers usable without a publisher API key"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 4, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.