There's An AI For That

Search MCPs

search_mcps

Read-only

Search and recommend MCP servers by name, description, capabilities, protocol tools, company, task, and category. The query is optional; use filters or sort to browse the directory.

Input Schema

Name	Required	Description
`sort`	No	Sort explicitly instead of using relevance for a query or popularity for an empty query.
`task`	No	Primary task, secondary task, or MCP category slug.
`limit`	No
`query`	No	Optional natural-language task, capability, server, company, or protocol-tool query.
`company`	No	Company slug.
`official`	No	True for official servers, false for community servers. Unclassified servers are excluded.
`auth_type`	No	Filter by the server authentication classification.
`transport`	No	Filter by remote HTTP/SSE or local stdio transport.

Output Schema

Name	Required	Description	Default
`mcps`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed17 schema fields changedOct 13, 2026

addedInput schema / properties / auth_type

Added value: +{
+  "description": "Filter by the server authentication classification.",
+  "enum": [
+    "none",
+    "api-key",
+    "oauth",
+    "other"
+  ],
+  "type": "string"
+}

addedInput schema / properties / company

Added value: +{
+  "description": "Company slug.",
+  "type": "string"
+}

changedInput schema / properties / limit / default
```
Previous value: -5New value: +20
```
changedInput schema / properties / limit / maximum
```
Previous value: -20New value: +50
```

addedInput schema / properties / official

Added value: +{
+  "description": "True for official servers, false for community servers. Unclassified servers are excluded.",
+  "type": "boolean"
+}

changedInput schema / properties / query / description

Previous value: -"The task or capability the user needs an MCP server for."New value: +"Optional natural-language task, capability, server, company, or protocol-tool query."

addedInput schema / properties / sort

Added value: +{
+  "description": "Sort explicitly instead of using relevance for a query or popularity for an empty query.",
+  "enum": [
+    "latest",
+    "popular",
+    "tools_count"
+  ],
+  "type": "string"
+}

addedInput schema / properties / task

Added value: +{
+  "description": "Primary task, secondary task, or MCP category slug.",
+  "type": "string"
+}

addedInput schema / properties / transport

Added value: +{
+  "description": "Filter by remote HTTP/SSE or local stdio transport.",
+  "enum": [
+    "remote",
+    "stdio"
+  ],
+  "type": "string"
+}

changedInput schema / required

Previous value: -[
-  "query"
-]New value: +[]

removedOutput schema / properties / mcps / items / properties / company_name
```
Removed value: -{
-  "type": "string"
-}
```
changedOutput schema / properties / mcps / items / properties / description / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```
addedOutput schema / properties / mcps / items / properties / entity_type
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / mcps / items / properties / id
```
Added value: +{
+  "type": "integer"
+}
```
removedOutput schema / properties / mcps / items / properties / tools_count
```
Removed value: -{
-  "type": "integer"
-}
```

removedOutput schema / properties / mcps / items / properties / url / description

Removed value: -"TAAFT MCP catalog page. Preserve this URL exactly when sharing it."

changedOutput schema / properties / mcps / items / required

Previous value: -[
-  "name",
-  "slug",
-  "description",
-  "company_name",
-  "tools_count",
-  "url"
-]New value: +[
+  "id",
+  "entity_type",
+  "name",
+  "slug",
+  "url"
+]

AddedSep 28, 2026

TDQS

A3.8/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds only that query is optional and the tool is a directory browser, consistent with the closed-world annotation but without detail on result shape, pagination, or recommendation ranking behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with purpose and closing with the query-optional constraint. Every clause carries information; nothing is padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 8 all-optional params, an output schema, and 88% schema coverage, the description only needs to explain the search-vs-browse split, which it does. It could mention that filters combine conjunctively or that limit caps at 50, but those gaps are minor given the structured fields.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 88%, so nearly every parameter is already documented in the schema (including the default-relevance/popularity behavior of sort). The description restates the optional-query semantics without adding format, slug syntax, or filter-combination guidance beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb pair (search/recommend) and resource (MCP servers), then enumerates the searchable dimensions (name, capabilities, company, task, category), which clearly separates it from get_mcp and search_tools. It never names a sibling explicitly, so differentiation is inferred from the field list rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

"The query is optional; use filters or sort to browse the directory" gives clear context for two distinct modes: relevance search vs. faceted browsing. There is no explicit when-not or pointer to get_mcp for single-server lookup, which would have made it a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All There's An AI For That tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.