Skip to main content
Glama

workspace_provider_keys

Manage this workspace's OWN provider API keys (bring your own key). action: list (default) shows every provider: configured, enabled for this workspace, when uploaded, never the key; set stores api_key for provider after the provider confirms it works, and enables it for THIS workspace; enable / disable switch this workspace's use of the key; delete removes the stored key. For video use provider gengen or byteplus: videos.generate then runs on your account, not the platform's. A key stored inside an integration is NOT used by these features. api_key also takes a clip: handle from clipboard.copy (pattern 'api_key'): a key someone sent in a chat is stored without anyone reading it. Needs ADMIN or OWNER in the workspace (list: any member). Where it is stored: keys live on the WORKSPACE OWNER's row and serve every workspace that owner owns. The owner may always set, replace or delete. An admin who is not the owner may set when the owner has no key for that provider, and may replace or delete only while no other workspace of the owner has the provider enabled; otherwise it is refused and the owner must do it. enable / disable touch only this workspace's switch.

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": "workspace_provider_keys"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionNolist | set | enable | disable | delete. OMIT for list.list
api_keyNoset only: the key, or a `clip:` handle from clipboard.copy (pattern 'api_key'). Never shown back. OMIT for every other action.
providerNoProvider id (see list). gengen and byteplus are the video providers. Required for set / enable / disable / delete; OMIT for list.
in_workspaceNoRun this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior4/5

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

Adds substantial behavior beyond annotations: the key is validated by the provider before storage, the key is never returned, keys live on the workspace owner's row and serve all of that owner's workspaces, and non-owner admins are refused in defined circumstances. One tension remains: destructiveHint=false while a delete action genuinely removes a stored credential, and the description does not clarify whether that removal is recoverable or the least-privileged path.

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?

Nearly every sentence carries unique information, and purpose is front-loaded before details. But the permission and storage-ownership rules arrive as an undifferentiated wall of prose, making the owner-vs-admin refusal logic slow to parse and easy to misread on a first pass.

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?

For a stateful, permission-gated credential tool this covers what an agent needs: action defaults, required parameters per action, authorization levels, storage ownership semantics, refusal conditions, and the fact that list never returns key material. No output schema exists, but the list result shape is described well enough.

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% and the clip: handle is already documented in the schema, so the baseline would be 3. The description still adds meaning by explaining why a clip: handle exists (a key pasted in chat is stored without a human reading it), that api_key is set-only and never echoed back, and which providers are the video ones.

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?

Names a specific resource (this workspace's OWN provider API keys, bring-your-own-key) and enumerates the five operations with their effects, so an agent knows exactly what the tool does. It also explicitly distinguishes itself from keys held inside integrations, which prevents confusion with siblings like agents_list_integrations.

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 per-action guidance (list is the default, set validates then enables, enable/disable flip only this workspace's switch, delete removes the stored key) plus prerequisites (ADMIN or OWNER; list open to any member). It also routes the video use case to gengen/byteplus and states which action to omit for which purpose, leaving little to inference.

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.