Trent

List connected sources

list_connected_sources

Read-only

List the workspace's connected platforms and the sources a project uses.

Omit project_id for connectors and their connections. An unconnected
connector includes connect_url. Send the customer there to connect it in
the app.

Pass project_id to also read its connected sources and each document's
source_kind: connector, push, or upload. This identifies, for example, a
report synced from Semgrep and a report uploaded by hand.

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_connected_sources"
  }
}

Input Schema

Name	Required	Description	Default
`project_id`	No	A Trent project id, to also list that project's sources. Omit for the workspace view.

Output Schema

Name	Required	Description
`error`	No	True when the call itself failed. False for successful calls, including a scan still running, an already approved plan, or a repository classified as non-agentic. The reason field describes these workflow states.
`reason`	No	A stable snake_case code from the allowed set. Present on every error and on successful calls that carry a workflow state.
`message`	No	Exactly one sentence written for the user. Never raw exception text or a backend error string, which may expose private details.
`sources`	No	The project's connected sources when project_id was given. Each includes its connector, title, status, last sync, sync policy, and platform link. Every document has source_kind: connector, push, or upload. Staged sources awaiting attachment appear under pending_sources.
`metadata`	No	Caller metadata, such as 'expiration_warning'. Substantive results have their own fields. Never includes exception or backend error text, which may expose private details.
`connectors`	No	Every connector Trent offers, with this workspace's connections. An unconnected connector includes connect_url, the app page where a person connects it.
`next_steps`	No	Recommended next actions, in order.
`project_id`	No	Resolved Trent project identifier, when one was given.
`document_count`	No	Documents the project holds now.
`document_limit`	No	The most documents a project holds.
`connections_url`	No	The app's connections page.
`pending_sources`	No	Sources staged for the project. Saving the project attaches them.
`retry_after_seconds`	No	With reason rate_limited, how many seconds Trent asks the caller to wait.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 30, 2026

addedOutput schema / properties / retry_after_seconds

Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "With reason rate_limited, how many seconds Trent asks the caller to wait.",
+  "title": "Retry After Seconds"
+}

First observedOct 23, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely useful behavior: unconnected connectors include a connect_url, and project mode returns source_kind values of connector, push, or upload. It does not discuss pagination, but with an output schema present that is a minor gap.

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?

The description is front-loaded with the core action, then splits into short paragraphs for the two modes. Each sentence carries actionable information: mode selection, connect_url behavior, and source_kind distinctions. There is no 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?

Given a read-only, single-optional-parameter tool with an output schema, the description provides everything needed: when to omit or include project_id, what the extra mode returns, and how to handle unconnected connectors. Return-value details beyond that are appropriately left to the output schema.

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 the baseline is 3. The description goes beyond the schema's parameter text by explaining the consequence of passing project_id in terms of returned data, such as distinguishing a synced report from a manually uploaded one. That adds useful semantic meaning to the single optional parameter.

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 and resource: 'List the workspace's connected platforms and the sources a project uses.' It also distinguishes the two operating modes (workspace-level connectors versus project-level sources), which is enough for an agent to separate this from siblings like find_related_sources or list_projects.

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 gives explicit conditional guidance: omit project_id for connectors/connections, pass project_id to also read sources. That covers when to use each mode clearly. It does not name alternative sibling tools or exclusion cases, so it falls short of a full when/when-not/alternatives statement.

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

All Trent 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.