Skip to main content
Glama

Pane

by com.paneui.relay

Manage App Service Credentials

credentials
Destructive

A v2 app's scoped service credentials (#1354, #1355): the bearer token an app owner points a backend they host themselves at, so their own server can read and write the app's data without holding the owner's full authority. Effective permission is always the intersection of the allowlist and what the app's owner could do, so a credential can only ever narrow, never widen, and it carries no role. Actions: mint creates one and returns its raw token shown once, never recoverable afterward (only its hash is stored); list returns the app's credentials with their allowlist and status, never any token material; pause reversibly stops one; resume undoes a pause (never a revoke, which is permanent); rotate issues a fresh token while the old one keeps working for an overlap window, so a running backend picks up the new token with no outage; revoke kills one permanently. Every action here is owner-or-owning-agent only: a service credential itself can reach none of these, by construction, so it can never mint or widen a sibling of itself.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNomint only. Defaults to explicit: an unnamed collection is denied, so the credential can never reach anything it was not handed (the shape for a contractor's backend). following: an unnamed collection falls through to the owner's own authority, so the credential tracks the app as it grows and each `grants` entry only narrows one collection (the shape for the owner's own backend). Neither mode can ever exceed what the app's owner could do; the effective permission is always the intersection.
labelNomint only. Optional owner-facing label shown in the credential list.
actionYesmint: create a scoped service credential, the bearer token an app owner points a backend they host themselves at (app_id; optional mode/grants/members/label/ttl_seconds). list: the app's credentials, their allowlist and status, never a token (app_id). pause: reversibly stop one, in force on its very next request (app_id+credential_id). resume: undo a pause; never undoes a revoke, which is permanent (app_id+credential_id). rotate: issue a fresh token and keep the old one working for an overlap window so a running backend picks it up without a gap (app_id+credential_id; optional overlap_seconds). revoke: kill one permanently and idempotently (app_id+credential_id).
app_idYesThe app id.
grantsNomint only. The allowlist: one entry per collection naming which of read/create/update/delete this credential may attempt there (an entry may name zero ops, which under `following` is how one collection is carved out of an otherwise app-wide credential). A collection named here must be a real declared collection on the app; a typo is rejected with a 400 rather than silently doing nothing.
membersNomint only. Opt in to the app's member directory appearing in this credential's boot/hello payloads. Defaults to false: a credential that never learns a member id cannot stamp one into a relation field.
ttl_secondsNomint only. Omit for the server's bounded default (365 days, clamped to a server maximum). null means no expiry, the explicit opt-in a long-running backend asks for; it is never the default.
credential_idNopause / resume / rotate / revoke. The credential id (see list's `id` field).
overlap_secondsNorotate only. How long the superseded token keeps resolving, so a running backend can pick up the new one with no gap. Defaults to the server default (1 day); 0 kills the old token immediately, the "this leaked" case.

TDQS

A4.6/5.0
Behavior5/5

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

Annotations indicate destructiveHint=true and readOnlyHint=false, but the description goes far beyond these by disclosing that tokens are shown only once and only hashes are stored, that pause is reversible while revoke is permanent, that rotate overlaps the old token, and that effective permissions are always the intersection with owner authority. It also explicitly states service credentials cannot access these actions, fully aligning with annotations and adding essential behavioral context.

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?

The description is a single dense paragraph that is information-rich with no fluff, but it could benefit from structured bullet points or short paragraphs for each action. Every sentence serves a purpose, though the lack of visual structure makes it slightly harder to scan quickly. It is appropriately sized for the tool's complexity.

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 the tool's complexity (6 actions, security nuances) and the absence of an output schema, the description thoroughly covers return behaviors (e.g., raw token shown once, list returns allowlist/status, rotate issues fresh token), side effects (pause/resume/revoke semantics), and access restrictions. It explains the security model of credential narrowing and the fact that credentials cannot self-manage, leaving no critical gaps for an agent to select and invoke the tool 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?

The input schema already provides rich descriptions for all parameters (100% coverage), so the baseline is 3. The description adds meaningful semantic context beyond the schema, particularly for 'mode' and 'grants' by explaining how they affect the credential's reach and the intersection permission model. However, some parameters like ttl_seconds, overlap_seconds, and members are only described in the schema, not in the tool description, so it doesn't fully compensate but still adds value.

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 identifies the tool as managing v2 app's scoped service credentials and enumerates all six actions (mint, list, pause, resume, rotate, revoke) with specific outcomes. It distinguishes this tool from potential siblings by emphasizing the scoped/bearer-token model and owner-only access, making the purpose unmistakable.

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?

The description explains when to use each action (e.g., mint for creating a credential for a backend, rotate for issuing a fresh token with overlap, revoke for permanent removal) and clarifies the access restriction (owner-or-owning-agent only). It does not explicitly name alternative tools or state when not to use this tool, but the context strongly implies its intended use case.

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

All Pane toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0
Disambiguation5/5

Each tool targets a distinct resource or action: row operations (get/list/upsert/update/delete/restore) are clearly separated, while apps, attachments, community, grants, ingest, members, publisher, review, and taste each cover a different domain. Even closely related actions like share_link_rotate and domain_set have clearly scoped descriptions, so an agent can reliably select the right tool.

Naming Consistency4/5

Tool names use two patterns: noun-like names for resource areas (apps, attachments, community, grants, ingest, members) and verb_noun names for row operations (upsert_row, delete_row, etc.). This deviation is predictable and readable, but it is not perfectly uniform, so a slight deduction applies.

Tool Count4/5

With 22 tools, the server is on the heavier side, but the breadth of the platform (app lifecycle, data storage, attachments, community, reviews, feedback, identity) justifies the count. Each tool represents a meaningful feature area with multiple internal actions, so none feels redundant.

Completeness5/5

The tool surface covers the full lifecycle for apps (create, read, update, delete), rows (create, read, update, delete, restore, list deleted), attachments, membership, grants, ingest, community, and reviews. Obvious gaps like rollback or version history are not core to the domain, and the presence of get_skill helps agents understand the workflow.

Resources