Find an MCP server for a task. See if its endpoint answers and what its tools cost in context.
Maintain this server? Claim it
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.
Compare 2 to 5 MCP servers side by side by slug: how each connects, licence, tool list, and what Stork's last check of each endpoint saw.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http mcp-directory 'https://mcp.stork.ai/mcp?tools=directory'
Compare 2 to 5 MCP servers side by side by slug: how each connects, licence, tool list, and what Stork's last check of each endpoint saw.
| Argument | Type | Description |
|---|---|---|
| slugs* | array |
{
"type": "object",
"required": [
"slugs"
],
"properties": {
"slugs": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 5,
"minItems": 2
}
}
}Ready-to-paste client config for one MCP server. Check installKnown first: when it is false, config is null because Stork holds no verified install method, and `instructions` links the publisher's own setup guide. Do not invent a command in that case. installMethod is 'remote' (connect by URL) or 'npm' (local stdio). authSummary says when the user must sign in.
| Argument | Type | Description |
|---|---|---|
| slug* | string | |
| client | string | The user's MCP client: cursor, claude-desktop, claude-code, vscode, zed. Any other name gets the common mcpServers JSON. |
{
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string"
},
"client": {
"type": "string",
"description": "The user's MCP client: cursor, claude-desktop, claude-code, vscode, zed. Any other name gets the common mcpServers JSON."
}
}
}Find an MCP server for a task. Say the task or product in plain words, for example: query Stripe payments, or browser automation. Results are ranked for an agent: the vendor's own server first, then servers you can connect to that answered Stork's last check. Each result is short: `connect` (remote URL or npm command, and whether sign-in is needed; null when Stork holds no install method), `publisherDomainVerified`, `toolNames`, and `check`: what Stork's own scheduled request to the endpoint last saw (result: answered | sign_in_required | stream_only | no_answer, lastCheckedAt, toolCount, toolDefinitionTokens = estimated tokens the tool definitions add to your context, toolsLastChangedAt, toolsChangedWithoutVersionChange). `check` is null for local stdio servers, which Stork cannot run. `confidence: weak` means nothing listed is a close match. A check is one initialize and one tools/list without an account: it does not prove a tool call works or that the server is safe. Listings that are duplicates of another listing, or that have not answered three checks in a row, are left out.
| Argument | Type | Description |
|---|---|---|
| limit | number | |
| query* | string | |
| category | string | |
| live_only | boolean | Only servers whose endpoint answered the last check without an account. |
| transport | string | |
| max_tool_tokens |
Get full details about a specific MCP server, including `check` (what Stork's last request to its endpoint saw, with the estimated token size of its tool definitions) and `toolChanges` (each time a check found different tool definitions than the check before, and whether the server's version changed with them).
| Argument | Type | Description |
|---|---|---|
| slug* | string |
{
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string"
}
}
}Find where an MCP server lives now that Smithery's hosted URLs are gone. Smithery's run.tools and server.smithery.ai URLs, its API, CLI and SDKs stopped on 2026-10-31. Pass the old URL (e.g. https://server.smithery.ai/@org/name/mcp or https://name.run.tools) or just the server name; returns listings that hold the server's own endpoint or npm package, with what Stork's last check of each endpoint saw. Matches are by name: confirm the publisher before connecting.
| Argument | Type | Description |
|---|---|---|
| reference* | string | Old Smithery URL, @org/name, or a server name |
{
"type": "object",
"required": [
"reference"
],
"properties": {
"reference": {
"type": "string",
"description": "Old Smithery URL, @org/name, or a server name"
}
}
}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 17, 2026.
| number |
| Only servers whose tool definitions are estimated at or under this many tokens. |
{
"type": "object",
"required": [
"query"
],
"properties": {
"limit": {
"type": "number",
"maximum": 10,
"minimum": 1
},
"query": {
"type": "string"
},
"category": {
"type": "string"
},
"live_only": {
"type": "boolean",
"description": "Only servers whose endpoint answered the last check without an account."
},
"transport": {
"enum": [
"stdio",
"sse",
"streamable-http"
],
"type": "string"
},
"max_tool_tokens": {
"type": "number",
"description": "Only servers whose tool definitions are estimated at or under this many tokens."
}
}
}