Skip to main content
Glama

Trust an external token issuer

set_trusted_issuer
Destructive

Configures a domain's JWT/API key endpoints to accept an identity provider's tokens by setting its issuer and required audience; can also replace an existing issuer.

Instructions

Makes the domain's jwt / apiKeyOrJwt endpoints accept tokens from an identity provider, or replaces the issuer of that name. issuer must be the exact iss the provider puts in tokens (Auth0's ends with "/", Entra's does not). audience is REQUIRED — the provider signs every app's tokens with the same keys. kind "jwks" (default) verifies RS/PS/ES against published keys; kind "hs256" verifies HS256 against a shared secret (Supabase's JWT secret, aud "authenticated") passed as secret — write-only, omit it to keep the stored one. The block then sees request.auth.issuer (the name) and request.auth.subject. Check it with check_trusted_issuer. Requires confirm=true.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "domainId": "<domainId>",
      "name": "<name>",
      "issuer": "<issuer>",
      "audience": "<audience>"
    },
    "name": "set_trusted_issuer"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNo"jwks" (published public keys, default) or "hs256" (a shared secret). Omit to keep an existing issuer's kind.
nameYesThe issuer's name on this domain, e.g. "auth0" — lowercase letters, digits, hyphens.
issuerYesThe issuer URL, exactly as the token's iss, e.g. "https://tenant.eu.auth0.com/".
secretNohs256 only: the shared secret tokens are signed with, at least 32 bytes. Never returned. Omit to keep the stored one.
confirmNoMust be true to act. Omit/false returns a preview only.
enabledNofalse keeps the configuration but refuses its tokens.
jwksUriNoOmit to find the keys through the issuer's discovery document.
audienceYesThe value the provider puts in aud for this API.
domainIdYesThe domain's id — from list_domains.
scopeClaimNoWhere the provider puts permissions: scope (default), scp (Entra, Okta), permissions (Auth0 RBAC), roles.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.53.0

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only declare destructiveHint, so the description carries the real weight and delivers: confirm=false returns a preview, secret is write-only and never returned, omitting secret/kind preserves stored values, and the block then sees request.auth.issuer/subject. The exact-iss nuance (Auth0 trailing slash vs Entra none) and the rationale for the required audience are behavior an agent cannot infer from structure.

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 action and the replace semantics, then constraints in descending importance; every sentence carries information. Density is high — heavy parentheticals and a dense final punch-list — which slightly hurts scannability but nothing is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter destructive mutation with no output schema, the description covers the critical unknowns: confirmation/preview behavior, secret write-only handling, defaults and preserve-on-omit semantics, and the downstream request.auth effect. Remaining gaps (permission requirements, failure modes) are minor for this tool class.

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 meaning beyond the schema: why audience is mandatory (the provider signs every app's tokens with the same keys) and the trailing-slash convention distinguishing Auth0 from Entra issuers. It doesn't add guidance on jwksUri, scopeClaim, or enabled beyond what the schema already documents.

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?

States a specific verb and resource — makes the domain's jwt/apiKeyOrJwt endpoints accept an IdP's tokens, or replaces an existing issuer of the same name — and explicitly routes verification to the check_trusted_issuer sibling. An agent can distinguish this from list/check/delete_trusted_issuer without opening schemas.

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?

Gives clear context ('or replaces the issuer of that name') and names check_trusted_issuer as the follow-up validation step, plus the confirm=true gating. It stops short of explicit when-not guidance (e.g., how this differs from delete_trusted_issuer for retirement), but the operational context is unambiguous.

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