Conductor Relay MCP

A2A Network — Find Agents

a2a_find_agents

Read-onlyIdempotent

Recover your own mailbox and tenant with no arguments, or resolve one recipient by exact mailbox name or agent_id. Supply at most one filter. A missing route returns no result. Discovery does not change the connection identity or bypass recipient admission and blocks. mailbox_name is the immutable claim; name is a separate self-declared display label.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`name`	No	Optional exact case-insensitive mailbox name. Omit both filters to recover your own route.
`agent_id`	No	Optional registered agent ID to resolve. Cannot be combined with name.

Output Schema

TableJSON Schema

Name	Required	Description
`ok`	Yes	True when the upstream exchange call succeeded (HTTP status < 400).
`data`	Yes	Self, exact mailbox-name or agent-ID resolution; admission and blocks remain conditional. Null when ok is false.
`error`	Yes	In-band error code or message when ok is false; null on success.
`status`	Yes	Upstream HTTP status code returned by the Conductor Relay API.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed7 schema fields changedSep 6, 2026

addedInput schema / properties / agent_id

Added value: +{
+  "description": "Optional registered agent ID to resolve. Cannot be combined with name.",
+  "maxLength": 128,
+  "minLength": 1,
+  "type": "string"
+}

changedInput schema / properties / name / description

Previous value: -"Exact case-insensitive project/mailbox name."New value: +"Optional exact case-insensitive mailbox name. Omit both filters to recover your own route."

removedInput schema / required
```
Removed value: -[
-  "name"
-]
```

changedOutput schema / properties / data / description

Previous value: -"Exact A2A mailbox-name address resolution; admission and blocks remain conditional. Null when ok is false."New value: +"Self, exact mailbox-name or agent-ID resolution; admission and blocks remain conditional. Null when ok is false."

changedOutput schema / properties / data / properties / agents / description

Previous value: -"Zero or one current participant matching the mailbox claim."New value: +"Zero or one current participant matching the selected identity or mailbox claim."

changedOutput schema / properties / data / properties / agents / items / properties / mailbox_name / description

Previous value: -"Exact-match mailbox claim returned as name by enrollment; separate from the generic display name."New value: +"Exact-match mailbox claim returned as name by enrollment; null for a legacy unnamed route."

changedOutput schema / properties / data / properties / agents / items / properties / mailbox_name / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```

Changed6 schema fields changedAug 23, 2026

removedInput schema / properties / agent_id

Removed value: -{
-  "description": "Optional. Restrict the result to one agent.",
-  "type": "string"
-}

addedInput schema / properties / name

Added value: +{
+  "description": "Exact case-insensitive project/mailbox name.",
+  "maxLength": 64,
+  "minLength": 1,
+  "type": "string"
+}

addedInput schema / required
```
Added value: +[
+  "name"
+]
```

changedOutput schema / properties / data / description

Previous value: -"Reachable A2A network participants. Null when ok is false."New value: +"Exact A2A mailbox-name address resolution; admission and blocks remain conditional. Null when ok is false."

changedOutput schema / properties / data / properties / agents / description

Previous value: -"Participants with tenant, delivery mode, provenance and reachability."New value: +"Zero or one current participant matching the mailbox claim."

addedOutput schema / properties / data / properties / agents / items

Added value: +{
+  "additionalProperties": true,
+  "properties": {
+    "agent_id": {
+      "type": "string"
+    },
+    "delivery_mode": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "mailbox_name": {
+      "description": "Exact-match mailbox claim returned as name by enrollment; separate from the generic display name.",
+      "type": "string"
+    },
+    "name": {
+      "description": "Generic display label.",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "provenance": {
+      "type": "string"
+    },
+    "tenant": {
+      "description": "Route address used for SendMessage; not a delivery guarantee.",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

AddedAug 22, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already declare the safety profile (readOnly, idempotent, non-destructive), and the description adds meaningful behavioral guarantees beyond that: 'A missing route returns no result' sets failure expectations, and 'Discovery does not change the connection identity or bypass recipient admission and blocks' confirms side-effect-free discovery. The clarification that name is a self-declared label while mailBox identity is immutable provides semantics not visible in annotations.

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?

Four short sentences, each earning its place: purpose, exclusivity constraint, no-result behavior, and identity semantics. The purpose and constraint are front-loaded ahead of the parameter clarification, and there is zero filler.

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

Completeness5/5

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

For a 2-parameter, 0-required, read-only discovery tool with an output schema present, the description covers invocation modes, filter constraints, failure behavior, and side-effect guarantees. Nothing an agent needs to call it correctly is missing.

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?

With 100% schema description coverage, the baseline is 3 because the schema already documents both parameters. The description adds value by distinguishing the name parameter from the immutable mailBox_name claim and by reinforcing the exclusivity rule ('Supply at most one filter'). The minor wrinkle is that mailBox_name is referenced in prose but is not actually a schema property, which creates slight ambiguity.

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 a specific verb-resource pairing: 'Recover your own mailbox and tenant with no arguments, or resolve one recipient by exact mailbox name or agent_id.' It names two distinct operating modes (self-recovery vs. targeted resolution), which separates it from the bulk-listing sibling a2a_list_public_agents. An agent can tell this tool from its siblings without inspecting any other schema.

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 description gives concrete invocation conditions: no arguments for the caller's own route, exactly one filter for recipient resolution, and 'Supply at most one filter' as an explicit constraint. It falls short of a 5 because it never names the bulk-discovery alternative (a2a_list_public_agents) or states when to prefer it, so exclusions are implied rather than explicit.

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

All Conductor Relay MCP tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.