Skip to main content
Glama

call_provider_api

Make a direct HTTP call to a provider's REST API when no MCP tool exists, using the named client's credential for Cloudflare, Vercel, or Resend.

Instructions

Make one HTTP call to a provider's own REST API with one client's credential.

Returns the status and the parsed body, plus a run_id. Every call is recorded as a mutation whatever the method, because an HTTP verb is a convention rather than a guarantee, and the response body is never written to the log.

Use this only when the provider's MCP server publishes no tool for the job: list_provider_tools first, call_provider_tool if it names one. Vercel publishes no environment-variable write and no project-domain attach, which is what this exists for. Works for cloudflare, vercel and resend, the three whose REST shape Munim knows.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bodyNoJSON request body, as an object.
pathYesA path beginning with one slash, for example /v9/projects. Never a full URL: an absolute URL is refused before the request is built, because it would send this client's credential to another host.
queryNoQuery string parameters, as an object.
clientYesThe client to act on, by the name you registered them under. A write resolves this one client's credentials and no other.
methodNoGET, POST, PATCH, PUT or DELETE. Every call is recorded as a mutation whatever the method, because an HTTP verb is a convention rather than a guarantee.GET
providerYescloudflare, vercel or resend. Only these three have a known REST base URL and header shape.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.5.0
    • addedInput schema / properties / body / description
      Added value: +"JSON request body, as an object."
    • addedInput schema / properties / client / description
      Added value: +"The client to act on, by the name you registered them under. A write resolves this one client's credentials and no other."
    • addedInput schema / properties / method / description
      Added value: +"GET, POST, PATCH, PUT or DELETE. Every call is recorded as a mutation whatever the method, because an HTTP verb is a convention rather than a guarantee."
    • addedInput schema / properties / path / description
      Added value: +"A path beginning with one slash, for example /v9/projects. Never a full URL: an absolute URL is refused before the request is built, because it would send this client's credential to another host."
    • addedInput schema / properties / provider / description
      Added value: +"cloudflare, vercel or resend. Only these three have a known REST base URL and header shape."
    • addedInput schema / properties / query / description
      Added value: +"Query string parameters, as an object."
  2. First observedv0.4.0

TDQS

A5/5.0
Behavior5/5

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

With no annotations, the description carries the full burden of behavioral disclosure. It states that every call is recorded as a mutation regardless of HTTP method, that the response body is never written to the log, and that absolute URLs are refused to prevent credential leakage. These are critical behavioral traits beyond the schema and are clearly articulated.

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 tight and front-loaded: the purpose is stated in the first sentence, followed by usage guidelines and provider specifics. Every sentence adds value—no filler. The structure flows logically from what it does to when to use it to how it behaves.

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?

Despite having no output schema, the description explicitly mentions that it returns 'the status and the parsed body, plus a run_id.' It covers the essential call contract, security constraints, and usage context. For a tool with 6 parameters, the description, combined with a fully described schema, leaves nothing an agent needs to correctly invoke it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description goes beyond the schema by explaining the path constraint (must start with slash, never a full URL) and the rationale for refusing absolute URLs. It also clarifies that the method field, despite being GET by default, is recorded as a mutation for any verb. This adds meaningful semantics to the parameters.

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 clearly states the action: 'Make one HTTP call to a provider's own REST API with one client's credential.' It specifies the resource (provider REST API) and explicitly differentiates from siblings by referencing list_provider_tools and call_provider_tool. The verb and target are unambiguous, and the scope is distinct from the other provider-related tools.

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?

Explicit guidance is given: 'Use this only when the provider's MCP server publishes no tool for the job: list_provider_tools first, call_provider_tool if it names one.' This names the alternatives and the condition for choosing this tool. It also provides concrete examples (Vercel env-var write, project-domain attach) and lists supported providers, leaving no ambiguity about when to invoke it.

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