Skip to main content
Glama
Sign In

Connections

by icu.connections
OverviewDiscussionsAdmin

List connected accounts/instances

connections_accounts
Read-only

THE answer to 'is connected?' - every connected account/instance this company has (service, instance, accountId, region), filterable with service and narrowed with match (looking for one plane's instance? pass match - the full list is ~50 rows). Pass an instance as connections_execute's instance to target one. Two kinds: a normal row holds a credential in this vault; a kind:'brokered' row is owned by ANOTHER first-party plane (named in via) that holds the credential - notably every Stripe account linked through Pay, which you reach with Pay endpoints per the row's callWith, NOT with service:'stripe'. Stripe can appear BOTH ways at once and they are different accounts: a brokered row is Pay's Connect link, while a normal stripe row is a secret key this workspace pasted directly and IS called with service:'stripe' as its own instance - so read the row's kind before choosing how to call it. A brokeredUnavailable field means that plane could not be reached, so the list is INCOMPLETE - never read it as 'not connected'.

Input Schema

NameRequiredDescriptionDefault
matchNoOnly accounts whose instance name, account name or account id contains this text (case-insensitive), e.g. 'accounts' for the Accounts plane. Instance names follow `<plane>@connections.icu` for most planes and `Main.Connections` for Main. Combines with `service`.
personNoLinked person to run this call as (first name). Omit to run as the connection's holder.
projectNoWorkspace to run this call in (id or name).
serviceNoOnly accounts for this service slug (aws, stripe, github, cloudflare, …). Omit for every connected account.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / person
      Added value: +{
+  "description": "Linked person to run this call as (first name). Omit to run as the connection's holder.",
+  "type": "string"
+}
  2. Changed1 schema field changed
    • addedInput schema / properties / project
      Added value: +{
+  "description": "Workspace to run this call in (id or name).",
+  "type": "string"
+}
  3. Changed1 schema field changed
    • addedInput schema / properties / match
      Added value: +{
+  "description": "Only accounts whose instance name, account name or account id contains this text (case-insensitive), e.g. 'accounts' for the Accounts plane. Instance names follow `<plane>@connections.icu` for most planes and `Main.Connections` for Main. Combines with `service`.",
+  "type": "string"
+}
  4. Changed1 schema field changed
    • addedInput schema / required
      Added value: +[]
  5. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only cover readOnly/openWorld; the description goes far beyond by disclosing the two row kinds (normal vs kind:'brokered'), that brokered credentials live in another plane named in `via`, that `callWith` determines how to call, and that a `brokeredUnavailable` field means the list is incomplete and must never be read as 'not connected'. That last point is a genuine correctness guard an agent could not infer.

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 the core answer and the execute hand-off before the nuance. It is a dense single block and the Stripe brokered-vs-normal explanation is repeated in slightly different words ('read the row's kind before choosing how to call it'), but nearly every clause carries operational consequence.

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?

No output schema exists, so the description carries the burden of describing the return shape, and it does: service, instance, accountId, region, kind, via, callWith, brokeredUnavailable. Combined with the incompleteness warning, an agent has everything needed to call it and interpret the result 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 coverage is 100%, so baseline is 3, but the description adds real meaning: `match` is for isolating one plane's instance because the full list is ~50 rows, and `service` is a slug filter that composes with match. It says nothing about `person` or `project`, but those are fully documented in the schema.

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?

Opens with a concrete framing ('THE answer to is <service> connected?') and then states exactly what is returned: every connected account/instance with service, instance, accountId and region. It is unmistakably distinct from siblings like connections_apps or connections_execute, and even names the hand-off relationship to connections_execute.

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 ('is <service> connected?'), how to narrow ('looking for one plane's instance? pass match'), the scale rationale (~50 rows), and the downstream action (pass an instance as connections_execute's `instance`). It also gives a critical exclusion: Stripe accounts brokered through Pay must be reached with Pay endpoints, not service:'stripe'.

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

All Connections toolsInspect
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.

Resources