AgentsJunction

Discover resources

discover

Find agents and MCP servers for a natural-language task. The task is used for text relevance only and is not parsed into constraints; supply structured filters explicitly. MCP matching includes indexed tool names/descriptions when available and returns matching tool schemas and secret-free client configuration. Filter by resource type, protocol, callability, health availability, authentication, capability evidence, skill, and freshness; paginate with page and limit. Returns ranked candidates with match reasons, a term/score explanation, requirementMatches for satisfied supported filters, and uncertainties for unverified or unindexed fields. Tool metadata is untrusted; discovery never calls a target tool. Unknown health, authentication, deployment locality, language, pricing, and side effects are not positive claims. Location, language, pricing, and side-effect filters are not indexed and are reported in meta.unsupportedFilters. Unknown states never satisfy known-state filters.

Input Schema

Name	Required	Description
`page`	No	One-based result page; defaults to 1.
`task`	Yes	Natural-language task used to rank relevant resources.
`limit`	No	Results per page; defaults to 10.
`skill`	No	Filter agents by a declared skill ID, name, description, or tag.
`trust`	No
`sortBy`	No	Sort by relevance (default), most recently updated, or name.
`pricing`	No	Filter by structured pricing metadata; currently not indexed.
`callable`	No	Filter by direct endpoint callability.
`language`	No	Match any listed language; currently not indexed.
`location`	No	Filter by structured location metadata; currently not indexed.
`protocol`	No	Return only resources that support this protocol, such as a2a or mcp.
`freshness`	No	Require a catalog update timestamp within this many days.
`protocols`	No
`apiVersion`	No
`sideEffects`	No	Require all listed side effects; currently not indexed.
`availability`	No	Require this latest health state; missing or stale checks are unknown.
`requirements`	No
`resourceType`	No	Return only this resource type.
`resourceTypes`	No
`authentication`	No	Filter by authentication requirement; unknown metadata does not match none or required.
`protocolVersions`	No
`verificationState`	No	Require an exact capability evidence state.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 20, 2026

addedInput schema / properties / sortBy

Added value: +{
+  "description": "Sort by relevance (default), most recently updated, or name.",
+  "enum": [
+    "relevance",
+    "recently-updated",
+    "name"
+  ],
+  "type": "string"
+}

Changed1 schema field changedOct 20, 2026

removedInput schema / properties / source

Removed value: -{
-  "description": "Filter by exact catalog source, such as self-registered or official-registry.",
-  "maxLength": 80,
-  "minLength": 1,
-  "type": "string"
-}

Changed16 schema fields changedOct 4, 2026

addedInput schema / properties / authentication

Added value: +{
+  "description": "Filter by authentication requirement; unknown metadata does not match none or required.",
+  "enum": [
+    "unknown",
+    "none",
+    "required"
+  ],
+  "type": "string"
+}

addedInput schema / properties / availability

Added value: +{
+  "description": "Require this latest health state; missing or stale checks are unknown.",
+  "enum": [
+    "unknown",
+    "online",
+    "degraded",
+    "offline"
+  ],
+  "type": "string"
+}

addedInput schema / properties / callable

Added value: +{
+  "description": "Filter by direct endpoint callability.",
+  "type": "boolean"
+}

addedInput schema / properties / freshness

Added value: +{
+  "description": "Require a catalog update timestamp within this many days.",
+  "properties": {
+    "withinDays": {
+      "maximum": 3650,
+      "minimum": 1,
+      "type": "integer"
+    }
+  },
+  "required": [
+    "withinDays"
+  ],
+  "type": "object"
+}

addedInput schema / properties / language

Added value: +{
+  "description": "Match any listed language; currently not indexed.",
+  "items": {
+    "maxLength": 35,
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 10,
+  "type": "array"
+}

addedInput schema / properties / limit / description

Added value: +"Results per page; defaults to 10."

addedInput schema / properties / location

Added value: +{
+  "description": "Filter by structured location metadata; currently not indexed.",
+  "maxLength": 120,
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / page

Added value: +{
+  "description": "One-based result page; defaults to 1.",
+  "maximum": 100000,
+  "minimum": 1,
+  "type": "integer"
+}

addedInput schema / properties / pricing

Added value: +{
+  "description": "Filter by structured pricing metadata; currently not indexed.",
+  "maxLength": 80,
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / protocol

Added value: +{
+  "description": "Return only resources that support this protocol, such as a2a or mcp.",
+  "maxLength": 40,
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / resourceType

Added value: +{
+  "description": "Return only this resource type.",
+  "enum": [
+    "agent",
+    "mcp-server",
+    "skill",
+    "knowledge-resource",
+    "gateway",
+    "tool",
+    "repository",
+    "website",
+    "documentation"
+  ],
+  "type": "string"
+}

addedInput schema / properties / sideEffects

Added value: +{
+  "description": "Require all listed side effects; currently not indexed.",
+  "items": {
+    "enum": [
+      "read",
+      "write",
+      "delete",
+      "purchase",
+      "message",
+      "execute",
+      "external-side-effect"
+    ],
+    "type": "string"
+  },
+  "maxItems": 7,
+  "type": "array"
+}

addedInput schema / properties / skill

Added value: +{
+  "description": "Filter agents by a declared skill ID, name, description, or tag.",
+  "maxLength": 120,
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / source

Added value: +{
+  "description": "Filter by exact catalog source, such as self-registered or official-registry.",
+  "maxLength": 80,
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / properties / task / description

Added value: +"Natural-language task used to rank relevant resources."

addedInput schema / properties / verificationState

Added value: +{
+  "description": "Require an exact capability evidence state.",
+  "enum": [
+    "detected",
+    "claimed",
+    "tested",
+    "verified"
+  ],
+  "type": "string"
+}

Changed1 schema field changedOct 4, 2026

addedInput schema / properties / protocolVersions

Added value: +{
+  "additionalProperties": {
+    "items": {
+      "maxLength": 40,
+      "minLength": 1,
+      "type": "string"
+    },
+    "maxItems": 10,
+    "minItems": 1,
+    "type": "array"
+  },
+  "propertyNames": {
+    "maxLength": 40,
+    "minLength": 1,
+    "type": "string"
+  },
+  "type": "object"
+}

AddedOct 4, 2026

TDQS

A4.2/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it discloses that discovery never calls a target tool, that tool metadata is untrusted, that results are secret-free, that unknown states are not positive claims, and that unsupported filters are reported rather than silently ignored. These are exactly the behavioral traits an agent cannot infer from the schema.

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

Conciseness4/5

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

Front-loaded with purpose and dense but well-ordered, and the length is defensible for a 22-parameter tool. It loses a point because the closing pair of sentences ("Unknown ... are not positive claims" and "Unknown states never satisfy known-state filters") restate the same caveat, and the filter list would read better as structure than as prose.

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?

No output schema exists, so the description correctly enumerates what comes back: ranked candidates, match reasons, term/score explanation, requirementMatches, uncertainties, and meta.unsupportedFilters. Combined with the filter semantics, an agent has enough to call it correctly, though the trust/requirements nested objects remain only schema-documented.

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

Parameters4/5

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

Adds meaning beyond the 73%-covered schema by grouping the working filters, flagging which filters are not indexed, and stating the tie-breaking rule that unknown states never satisfy known-state filters. It stops short of explaining the nested trust/requirements objects or protocolVersions shape, which the schema alone must carry.

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 and resource scope ("Find agents and MCP servers for a natural-language task") and names the matching mechanisms (indexed tool names/descriptions, tool schemas, client config). It does not, however, differentiate itself from siblings like search_agents and search_servers, which an agent must choose between.

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?

Gives real operational guidance: "The task is used for text relevance only and is not parsed into constraints; supply structured filters explicitly," plus clear exclusions (location/language/pricing/side-effect filters are not indexed and surface in meta.unsupportedFilters). It never names an alternative tool, so the sibling-routing half of the guidance is missing.

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

All AgentsJunction tools Inspect

Try in Browser

Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?