Skip to main content
Glama

Manage App Connections

connections
Destructive

A v2 app's Connections: the stored credential (a static header token, or a full generic OAuth2 client) a manifest webhook rule authenticates its delivery target with, bound to a host so the credential can never be exfiltrated to another one. There is no update action: change a connection by deleting and recreating it. Actions: create stores a static or oauth2 connection and returns its metadata, never the secret; list returns the app's connections as metadata plus a non-reversible fingerprint, never any secret; delete is idempotent; consent_url builds (never fetches) the browser URL that completes an oauth2 connection's consent, since that is inherently a human-in-a-browser step an agent key cannot complete. A newly created oauth2 connection starts in pending_auth until the owner opens the consent_url and approves.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kindNocreate only. Defaults to `static`.
nameNocreate / delete / consent_url. The connection name (lowercase, starting alphanumeric, up to 64 chars) that a manifest webhook rule's `connection` field references.
labelNocreate only. Optional owner-facing label.
actionYescreate: store a webhook connection, a stored credential (static header token or a full generic OAuth2 client) a manifest webhook rule authenticates its target with (app_id+name+allowed_host, plus kind-specific fields). list: the app's connections as metadata plus a non-reversible fingerprint, never any secret (app_id). delete: idempotent (app_id+name). consent_url: build (never fetch) the browser URL that completes an oauth2 connection's owner consent (app_id+name); hand it to the signed-in owner to open, since an agent key cannot complete OAuth consent itself.
app_idYesThe app id.
scopesNocreate only (oauth2). Space-delimited scopes for the authorize request.
providerNocreate only. Freeform display label only, e.g. "hubspot"; not validated against any allowlist.
client_idNocreate only, required for kind=oauth2. Your OAuth2 app's client id.
auth_paramsNocreate only (oauth2). Extra key/values merged into the authorize redirect (e.g. to request offline access).
auth_schemeNocreate only (oauth2). The scheme the access token is sent under. Defaults to "Bearer"; set e.g. "Zoho-oauthtoken" for a non-Bearer provider.
header_nameNocreate only (static). The header the credential rides in. Defaults to "Authorization".
allowed_hostNocreate only, required for both kinds. The host-binding exfiltration defence: an exact DNS host ("api.hubapi.com") or a single leftmost wildcard ("*.zohoapis.com"). The stored credential is attached to a delivery only when its url host matches; a rule later repointed elsewhere fails delivery rather than sending the secret to the wrong host.
header_valueNocreate only, required for kind=static. The header value to send, e.g. "Bearer sk_live_...". Encrypted at rest and never returned by any call.
token_paramsNocreate only (oauth2). Extra key/values merged into the token POST.
authorize_urlNocreate only, required for kind=oauth2. The provider's OAuth2 authorize endpoint (https; rejected if it resolves to a private/loopback/metadata address).
client_secretNocreate only, required for kind=oauth2. Your OAuth2 app's client secret. Encrypted at rest and never returned by any call.
instance_fieldNocreate only (oauth2). The name of a token-response JSON field holding the API base URL (e.g. "instance_url"). When set, the relay re-binds allowed_host to that host after consent and resolves relative rule urls against it.
token_endpointNocreate only, required for kind=oauth2. The provider's OAuth2 token endpoint (same https + SSRF rules as authorize_url).

TDQS

A4.4/5.0
Behavior5/5

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

Beyond annotations (readOnlyHint=false, destructiveHint=true), the description reveals critical behavior: create "returns its metadata, never the secret," list returns a "non-reversible fingerprint, never any secret," delete is idempotent, and oauth2 connections start in `pending_auth` until consent. It also explains the host-binding failure mode, providing substantial transparency.

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 long, but it is well-structured and information-dense, covering all major actions and edge cases. It fronts the core concept, then follows with the no-update caveat and action breakdown. While not maximally concise, every sentence contributes useful context.

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 (4 actions, 18 params, no output schema), the description is remarkably complete. It explains return values (metadata vs secret/fingerprint), the pending_auth state, the consent flow, idempotency, and the host-binding security model. No major behavioral gaps remain.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description does not add significant per-parameter meaning beyond what the schema already provides; it summarizes high-level behavior but points to the schema for field-level semantics.

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 states the tool's purpose and differentiates its actions: "Actions: create stores...; list returns...; delete is idempotent; consent_url builds..." Each action has a specific verb and resource, making the tool's role unambiguous. It also distinguishes connections from generic credentials by emphasizing the host-binding exfiltration defence and webhook authentication context.

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 provides actionable when-to-use guidance, notably "There is no update action: change a connection by deleting and recreating it" and the note that consent_url is for a "human-in-a-browser step an agent key cannot complete." It does not explicitly compare against sibling tools like 'credentials', but the context is sufficient for most use cases.

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.

TDQS

A4.1/5.0
Disambiguation4/5

Most tools are clearly distinct, with row operations (list, get, upsert, update, delete, restore) well separated. Some boundaries like apps vs deploy_app and credentials vs grants require careful reading, but descriptions resolve the overlap.

Naming Consistency2/5

Tool names mix resource nouns (apps, attachments, connections) with verb_noun actions (delete_row, deploy_app). Singular and plural forms are inconsistent, and there is no uniform pattern across the set.

Tool Count3/5

24 tools is on the heavy side, but the platform's breadth (app deployment, data, auth, community) justifies the count. Each tool has a distinct role, though the set slightly exceeds the typical well-scoped range.

Completeness4/5

The surface covers the full app lifecycle: deploy, manage, delete, row CRUD with restore, attachments, credentials, and community features. Minor gaps like no dedicated row search or outbound webhook management are workable via existing tools.