Skip to main content
Glama

Get a fresh credential link

request_connection_link

Mint a fresh credential link for a service datasource. Native MCP connections re-link in place; their hosted page uses Test and finish (or OAuth sign-in), and ready connections require reconnect: true. A Custom OAuth datasource keeps its declared resource and optional scopes; the Administrator must open the credential page and sign in on the hosted page, with no pasted token. Initial setup becomes ready only after sign-in completes. For a ready oauth2_auth_code datasource or external_platform card, explicitly pass reconnect: true to sign in again while keeping the connection, any published module and approvals. Failed OAuth connections and platform cards also re-link in place. The status and serving grant stay as the Request Service reports until sign-in succeeds; failed or declined re-sign-in keeps the serving grant. A typed-credential page still configuring is renewed for the same connection. A Custom datasource published against a card renews the page of its own credential connection, which its module pins, when configuring or failed, or ready with reconnect: true. A ready, unbound typed-credential connection (env) also renews in place with explicit reconnect: true once it owes no Data Access key. Either renewal keeps the connection, any published module and its approvals, and a bound one its card binding; stored credentials stay in force until replacements are saved. Only an Administrator can open a renewed page, bound or unbound, so give the link to an Administrator rather than to whoever asked: the replacement is written to the account of the Administrator who opens it, or to the shared set where the connection is shared. Without reconnect, a ready connection that owes nothing is refused with already_connected. Outside sign-in, MCP and card-bound connections, one that still owes its Data Access key is replaced instead, configuring or ready, which delivers a fresh key and asks for the credentials again (a ready one only without reconnect). For a ready connection that still owes its Data Access key, rotating the Data Access Point's key again (Rotate key on the Data Access Points page in Admin, /projects/{project_id}/data-access-points) restores it on the same connection; a new link replaces the connection and the person must enter the credentials again. The person enters replacements on the Request Service's page or consents on the platform page; a typed re-link finishes with Save credentials and finish, while MCP uses Test and finish or its OAuth sign-in action. A newly minted link lasts one hour from issue; opening or reloading does not use it up, and successful completion does. The credential never passes through this conversation. Requires the project's datasource-management grant and an Administrator caller.

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": {
      "datasource_id": "<datasource_id>"
    },
    "name": "request_connection_link"
  }
}

Input Schema

NameRequiredDescriptionDefault
reconnectNoExplicitly reconnect a native MCP connection, request sign-in again for an oauth2_auth_code datasource or external_platform card, or replace typed credentials in place on an unbound connection or a card-bound Custom datasource's own connection; required when ready, default false
datasource_idYesThe service datasource UUID
application_idNoOptional Application UUID whose build this call serves (Administrator only). Setup steps this call opens record it, so they show on that Application's build screen; the resources themselves stay shared by the Project. A shared step it reuses keeps the Application it was opened for, so a step it returns may be watchable with get_setup_journal only without application_id. Use the build's application_id, the one you call describe_application with.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Goes well beyond annotations: the link expires in one hour from issue, opening/reloading does not consume it, successful completion does, and the credential never passes through the conversation. It also spells out authorization requirements (datasource-management grant plus an Administrator caller) and precisely what state survives re-link -- published modules, approvals, card binding, stored credentials until replacements are saved -- and what happens to status and serving grant on failure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening sentence is well front-loaded, but the rest is a ~450-word wall of overlapping conditionals with repeated phrasing about re-linking in place and preserving modules/approvals. The Administrator warning, expiry rule, and already_connected behavior are the load-bearing facts and are buried mid-paragraph rather than structured.

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 tool with no output schema and a highly branched behavioral contract, the description covers what an agent needs: when reconnect is required, what is preserved or replaced, who must open the link, and the link's lifetime. Nothing material appears missing.

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 the baseline is 3, but the prose adds real meaning: reconnect is required when ready, is refused otherwise with already_connected, and has different effects across oauth2_auth_code, external_platform, MCP and typed-credential connections. application_id semantics are covered in the schema itself, and the description adds little there.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Mint a fresh credential link for a service datasource" gives a specific verb and resource, and the body clarifies it produces a hosted page rather than passing a credential through the conversation. It never names a sibling tool (e.g. connect_datasource or set_datasource_credential_mode) to contrast against, so differentiation is left to inference.

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 gives strong conditional guidance: pass reconnect: true for ready connections, expect already_connected without it, and prefer 'Rotate key' on the Data Access Points page for a ready connection that still owes its key. It also states who may use the result (give it to an Administrator). The guidance is present but buried in a dense stream, making the branching hard to follow on first read.

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.

Resources