Skip to main content
Glama

List the organization's connectors

list_connectors
Read-onlyIdempotent

List the organization's connectors: each one's name, kind, transport, catalog entry, and description. It is the discovery step before attach_connector.

Pass name to judge each connector against one website, app, or agent: every row then says whether that service can hold the connector and whether it holds it now. A website can hold only an mcp-server connector on the sse or streamable-http transport, because a page reaches a connector through Valet's gateway; the rows a website cannot hold are marked, not hidden. An agent can hold any of them. An app cannot hold a connector yet.

Tool schemas are not included: to see a connector's tools, call list_connector_tools with the connector's name. Attach a connector to a website only when the user asks to give the site's pages access, since attaching hands the connector's reach to everyone who can open the site. Returns one row per connector, and with name, the service the rows' can_hold and attached are judged against. Requires connecting a Valet account.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_connectors"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoThe website's, app's, or agent's name. Each row then says whether it can hold the connector and whether it holds it now. Omit for the plain organization-wide list.
org_nameNoThe Valet organization whose connectors to list. Omit to use the organization the account joined first.

Output Schema

NameRequiredDescriptionDefault
orgYesName of the Valet organization the call acted in.
kindNoKind of the service named in name: site, app, or agent. Absent when the call named none.
nameNoName of the website, app, or agent the can_hold and attached markers are judged against. Absent when the call named none.
connectorsYesThe organization's connectors. Empty when it has none.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changed
    • addedOutput schema / properties / connectors / description
      Added value: +"The organization's connectors. Empty when it has none."
    • addedOutput schema / properties / connectors / items / properties / attached / description
      Added value: +"True when the service named in the call already holds this connector. Absent when false or when the call named no service."
    • addedOutput schema / properties / connectors / items / properties / can_hold / description
      Added value: +"Whether the service named in the call can hold this connector. Absent when the call named no service."
    • addedOutput schema / properties / connectors / items / properties / catalog / description
      Added value: +"Name of the catalog entry the connector came from. Absent for a custom connector."
    • addedOutput schema / properties / connectors / items / properties / description / description
      Added value: +"The catalog entry's description. Absent for a custom connector or one whose catalog entry is no longer live."
    • addedOutput schema / properties / connectors / items / properties / kind / description
      Added value: +"The connector's type: mcp-server or command."
    • addedOutput schema / properties / connectors / items / properties / name / description
      Added value: +"The connector's name, which attach_connector takes."
    • addedOutput schema / properties / connectors / items / properties / transport / description
      Added value: +"How the connector's server is reached, such as streamable-http or sse. Absent for a command connector."
    • addedOutput schema / properties / kind / description
      Added value: +"Kind of the service named in name: site, app, or agent. Absent when the call named none."
    • addedOutput schema / properties / name / description
      Added value: +"Name of the website, app, or agent the can_hold and attached markers are judged against. Absent when the call named none."
    • addedOutput schema / properties / org / description
      Added value: +"Name of the Valet organization the call acted in."
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": false,
      +  "properties": {
      +    "connectors": {
      +      "items": {
      +        "additionalProperties": false,
      +        "properties": {
      +          "attached": {
      +            "type": "boolean"
      +          },
      +          "can_hold": {
      +            "type": [
      +              "null",
      +              "boolean"
      +            ]
      +          },
      +          "catalog": {
      +            "type": "string"
      +          },
      +          "description": {
      +            "type": "string"
      +          },
      +          "kind": {
      +            "type": "string"
      +          },
      +          "name": {
      +            "type": "string"
      +          },
      +          "transport": {
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "name",
      +          "kind"
      +        ],
      +        "type": "object"
      +      },
      +      "type": [
      +        "null",
      +        "array"
      +      ]
      +    },
      +    "kind": {
      +      "type": "string"
      +    },
      +    "name": {
      +      "type": "string"
      +    },
      +    "org": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "org",
      +    "connectors"
      +  ],
      +  "type": "object"
      +}
  3. Added

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare this a safe, idempotent, non-open-world read, so the safety profile is covered. The description adds genuinely new behavior: rows that a website cannot hold are marked rather than hidden (so an empty filter is not an error), and it discloses an authentication prerequisite ('Requires connecting a Valet account') plus the security consequence of the adjacent attach action (it hands the connector's reach to everyone who can open the site).

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

Conciseness3/5

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

The first sentence front-loads purpose and next step well, and the field list is efficient. However the block is long and loosely joined, stacking the website/app/agent capability rules, a tools-schema disclaimer, and attach-prerequisite advice into one paragraph, so several clauses about the attach sibling dilute focus on a read-only list operation.

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?

Given an output schema exists, the description needn't explain return formatting, and it still summarizes the row shape. It covers auth requirement, the semantics of the filter, capability constraints per service type, sibling routing, and the safety implication of the follow-on attach, which is everything an agent needs to call this correctly.

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?

Schema description coverage is 100%, so baseline is 3, but the description adds real meaning: it explains what the name parameter actually changes in the output (each row's can_hold and attached are judged against that service) and encodes domain rules the schema cannot express, namely that websites only hold mcp-server connectors on sse or streamable-http while agents can hold any and apps cannot hold any yet.

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?

Names a specific verb and resource (list the organization's connectors) and immediately enumerates what each row carries: name, kind, transport, catalog entry, description. It also distinguishes itself from list_connector_tools (tool schemas are elsewhere) and from attach_connector (this is the discovery step before it), so an agent can route correctly without opening the schema.

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

Usage Guidelines5/5

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

Gives explicit when-to-use guidance for the optional name parameter (pass it to judge connectors against one website, app, or agent), explicit when-not guidance for the follow-on action ('Attach a connector to a website only when the user asks to give the site's pages access'), and names the alternative for tool details. Little is left to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources