agentswitchboard

Search Agents

search_agents

Search the Agent Switchboard directory of vetted AI agents, MCP servers, and agentic tools. Returns relevance-ranked matches. Filter by category slug and/or access methods.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Max results per page (1–50)
`query`	No	Free-text search (name, description, skills, tags)
`access`	No	Require ALL of these access methods (api, mcp, cli, browser-extension)
`offset`	No	Number of results to skip, for pagination
`category`	No	Category slug, e.g. "code-devtools", "voice-messaging"

Output Schema

TableJSON Schema

Name	Required	Description
`limit`	Yes
`total`	Yes	Total matches before paging
`agents`	Yes
`offset`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedSep 18, 2026

addedInput schema / properties / limit / description
```
Added value: +"Max results per page (1–50)"
```

addedInput schema / properties / offset

Added value: +{
+  "default": 0,
+  "description": "Number of results to skip, for pagination",
+  "minimum": 0,
+  "type": "integer"
+}

addedOutput schema / properties / limit
```
Added value: +{
+  "type": "integer"
+}
```
addedOutput schema / properties / offset
```
Added value: +{
+  "type": "integer"
+}
```
addedOutput schema / properties / total / description
```
Added value: +"Total matches before paging"
```

changedOutput schema / required

Previous value: -[
-  "total",
-  "agents"
-]New value: +[
+  "total",
+  "offset",
+  "limit",
+  "agents"
+]

Changed1 schema field changedSep 18, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "agents": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "accessMethods": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "authType": {
+            "type": "string"
+          },
+          "categories": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "description": {
+            "type": "string"
+          },
+          "name": {
+            "type": "string"
+          },
+          "provider": {
+            "type": "string"
+          },
+          "slug": {
+            "type": "string"
+          },
+          "url": {
+            "type": "string"
+          },
+          "verified": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "name",
+          "slug",
+          "description",
+          "provider",
+          "categories",
+          "accessMethods",
+          "authType",
+          "verified",
+          "url"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "total": {
+      "type": "integer"
+    }
+  },
+  "required": [
+    "total",
+    "agents"
+  ],
+  "type": "object"
+}

First observedJul 24, 2026

TDQS

A4/5.0

Behavior3/5

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

With no annotations, the description carries the burden of behavioral context. It discloses meaningful behavior beyond the schema: results are relevance-ranked, the directory is curated ('vetted'), and filters can be combined. It does not explicitly state that the operation is read-only or describe pagination behavior, but 'search' strongly implies a safe read operation.

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?

Three short sentences front-load the action, resource, and result, then add the filtering capability. There is no redundant restatement of the tool name or schema.

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?

The description is adequate for a search tool with five optional, fully documented parameters and an output schema. It covers what is searched, what is returned, and the key filtering dimensions, although it does not explicitly mention pagination or route the agent to sibling tools.

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 coverage is 100%, so the baseline is 3; the schema already documents limit, offset, query, access, and category. The description adds a small clarification by saying filters can be applied by category and/or access methods, but it does not add deeper meaning to the remaining parameters.

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

Purpose5/5

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

The description opens with the verb 'Search' and names a concrete resource: 'the Agent Switchboard directory of vetted AI agents, MCP servers, and agentic tools.' It also states the result type ('relevance-ranked matches'), which separates it from the sibling tools get_agent and list_categories.

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?

It clearly frames the tool as a directory search rather than a category listing or single-agent fetch, so the broad usage context is evident. It does not explicitly name get_agent or list_categories or state when not to use those alternatives, though the 'search' framing makes the distinction largely inferable.

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

All agentswitchboard 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.