Skip to main content
Glama

TracePass access grants

tracepass_access_grants
Destructive

Share restricted passport data with a partner (repairer, recycler, purchaser...) through an access grant, and see or end the grants already issued. A grant names a role, a scope (company, chosen products or chosen passports), a purpose, optional evidence and an expiry (default 12 months). Needs an OAuth connection approved for access grants or an API key with "May manage access grants" switched on (403 access_grants_not_enabled); writing needs an admin. Authority roles (e.g. market surveillance) are dashboard-only end to end: create, update and revoke of such a grant are refused (400 role_dashboard_only).

IMPORTANT: create returns the secret pa_ token ONCE. Hand it to the recipient and do not repeat it, store it or put it in a log. It cannot be shown again; if lost, revoke the grant and create a new one. A confirmed grant gives a third party access to restricted data: confirm the recipient, role, scope and purpose with the user first.

Actions (pass via action; {…} is the args object). Reads never return a token.

  • list — { limit? (≤100), cursor?, role?, status? (active|expired|revoked), passportId?, productId? }.

  • get — { id }.

  • create — { role, label, purpose?, scope? ({ kind: company } with no ids, or { kind: products|passports, ids[] } with at least one id), evidence? ({ type: register_entry|invoice|authority_letter|contract|other, reference, note? }), expiresInDays? (1-1825; null = no expiry) }. WRITE.

  • update — { id, label?, purpose?, scope?, evidence?, expiresInDays? }; at least one. WRITE.

  • revoke — { id }. WRITE, ends the grant at once; repeating it is safe.

  • activity — { id, limit? (≤100), cursor? }. The grant's access log.

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": {
      "action": "<action>"
    },
    "name": "tracepass_access_grants"
  }
}

Input Schema

NameRequiredDescriptionDefault
argsNo
actionYes

Output Schema

NameRequiredDescriptionDefault
idNo
pageNo
errorNo
itemsNo
limitNo
totalNo
resultNo
messageNo
totalPagesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations (destructiveHint=true, readOnlyHint=false), it discloses the critical asymmetry the annotations cannot express: create returns the pa_ secret token exactly once, it is unrecoverable, and loss requires revoke-then-recreate. It also notes reads never return a token and that revoke is safe to repeat, which is exactly the operational nuance an agent needs before a destructive write.

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?

Three blocks—what it does, the security warning, then a compact per-action argument table—with the irreversible-token warning front-loaded before any action detail. Dense but every line carries either a permission rule, an error code, or an argument constraint that the schema does not express.

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?

An output schema exists, so return values need not be restated, and the description fills the remaining gaps for a multi-action write tool: auth paths, specific error codes (403 access_grants_not_enabled, 400 role_dashboard_only), the one-time token, and idempotency of revoke.

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 0%, so the description does all the work—and it does: per-action arg lists, limit ≤100, the status enum (active|expired|revoked), scope's discriminated shape (kind: company with no ids vs products/passports requiring at least one id), evidence type enum, and expiresInDays bounds 1–1825 with null meaning no expiry.

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 sentence gives a specific verb and resource: share restricted passport data with a partner through an access grant, and see or end existing grants. It also enumerates the six actions (list, get, create, update, revoke, activity) in a way that makes the tool's envelope unmistakable, and no sibling covers grant management.

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?

It states prerequisites clearly (OAuth connection approved for access grants or API key with 'May manage access grants'; admin needed for writes) and gives an explicit exclusion: authority roles such as market surveillance are dashboard-only and will be refused with 400 role_dashboard_only. It also directs the agent to confirm recipient, role, scope and purpose with the user before creating. It stops short of naming a sibling tool as the alternative for adjacent operations, hence a 4 rather than 5.

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.