Skip to main content
Glama

List service providers

list_service_providers
Read-onlyIdempotent

List the service providers a datasource can be created on: "custom" (a connector this conversation will write), answered on its own as custom, and one page of the Request Service's catalogue cards, each with the credentials its page asks for (name, label, secret, required, help), its operations and documentation where available. MCP cards omit docs_url. q searches the catalogue, at most 128 bytes. Each word of q must begin a word of a card's id, name or description, ignoring case. group narrows the answer to one slug from its groups, which count the search's cards in each group before group and paging narrow them. page is the one-based page to read, 1 by default. limit is how many cards a page holds, 20 by default and at most 200. total counts the cards the search and group match, not the cards on this page, and never counts custom or native_databases. The answer also lists native databases matching q in native_databases, using a case-insensitive substring of their name or search terms. Native databases appear only on page 1 when group is empty or databases; otherwise native_databases is an empty array, never null. They do not contribute to total or groups; an empty q lists them all when shown. Connect an entry in native_databases with connect_datasource, using the entry's connect_datasource arguments (type, and provider where present) together with a datasource name agreed with the person. The entry's name is the card's label, not a datasource name; it is not a service or Custom connector. Search with a word of the service's name rather than reading the catalogue page by page. Read this before create_service_datasource, and agree the service, its purpose and its credentials with the person first. Names only: no value passes through this conversation. Cards with source mcp or connect mcp require an mcp declaration; directory cards default its URL from mcp.url and never use Composio sign-in. Stands before any datasource exists.

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_service_providers"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoWords that each begin a word of a card's id, name or description, ignoring case
pageNoThe one-based page to read (default 1)
groupNoOne group slug from the answer's groups, such as "crm"
limitNoCards per page (default 20, max 200)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations it discloses non-obvious behaviors that would otherwise cause wrong calls: q is capped at 128 bytes, total counts search+group matches and never custom or native_databases, native_databases appears only on page 1 when group is empty or 'databases' and is an empty array rather than null otherwise, and MCP cards omit docs_url. It also flags a safety-relevant fact ('Names only: no value passes through this conversation') and an auth/declaration requirement for mcp sources.

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 purpose is front-loaded and no sentence is pure filler, but the body is a wall of run-on sentences that repeat schema facts ('1 by default', '20 by default and at most 200') and bury the connect_datasource handoff mid-paragraph. It is dense rather than wasteful, yet restructuring into scoped bullets would preserve every fact with far less scanning cost.

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?

With no output schema, the description carries the burden of describing the return shape and does so — cards, their credential fields, groups, total, native_databases and their null-vs-empty edge case. For an open-world, paginated, filter-driven listing tool, an agent has everything needed to call it and interpret the reply.

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 the baseline is 3, but the description earns extra by adding semantics the schema omits: the 128-byte cap on q, the prefix-matching rule, and the ordering detail that groups count the search's cards 'before group and paging narrow them'. The remaining duplication of page default and limit max is redundant with the schema rather than additive.

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 opening clause names a specific verb and resource — 'List the service providers a datasource can be created on' — and immediately decomposes the result into three distinct populations (custom, catalogue cards, native_databases). It also pins its position in the workflow with 'Stands before any datasource exists' and 'Read this before create_service_datasource', so an agent can separate it from the write-side siblings.

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?

It gives explicit when-to-use direction ('Search with a word of the service's name rather than reading the catalogue page by page'), an explicit sequencing rule ('Read this before create_service_datasource, and agree the service... with the person first'), and an explicit handoff to a different tool for one branch ('Connect an entry in native_databases with connect_datasource, using the entry's connect_datasource arguments'). Both alternatives and the conditions that select them are named.

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