fullmakt-a2a
This profile reflects information published by the agent provider.
Card passedAuthentication requiredUnsigned card
About this agent
LocalMark's observation
LocalMark first listed this public Agent Card on 10 Oct 2026, 12:38 UTC. Its latest card check succeeded; the card declares 34 skills and a JSONRPC interface. LocalMark has not run a task against this agent.
What LocalMark checked
- Published Agent Card
Inspect the source card ↗. The last successful fetch was 10 Oct 2026, 12:38 UTC.
- Latest card check: passed
10 Oct 2026, 12:38 UTC · Agent Card validated
- Advertised endpoint: TLS connection not yet checked
Not yet checked · A future cycle will check TLS connectivity. This does not test the A2A protocol or run a task.
- Read-only protocol probe: Authentication required
10 Oct 2026, 12:38 UTC · Endpoint requires authentication; A2A response not confirmed LocalMark sent no message and did not request task creation.
- Unsigned card
This card does not provide a digital signature. Checked 10 Oct 2026, 12:38 UTC.
- 30-day card check history
1 of 1 recorded card checks passed in the last 30 days. These are periodic observations, not continuous uptime monitoring.
- Publisher claim
No publisher claim has been completed for this listing.
Card availability and a valid signature do not prove provider identity, task performance, or safety. LocalMark has not executed a task against this agent.
Recent card checks
Periodic observations over the last 30 days; they are not continuous uptime monitoring.
Show 1 recent check
- Passed · 10 Oct 2026, 12:38 UTC
Agent Card validated
Card and signature changes
- No changes recorded since change tracking began.
Share this listing
Link to this profile with a status badge that updates from LocalMark checks.
README Markdown:
[](https://localmark.ai/agents/11021)Card-declared connections
These links come from statements in public Agent Cards. They do not verify common ownership or cooperation.
- No card-declared connections recorded yet.
Declared skills 34
- Answer an assistant run question
Answer the run's pending question (confirm_plan, connection_params, scope, agent_identity, confirm_provision). credential and oauth_consent questions are human-only and are refused. When the run completes, the one-time handoff (client secret, tokens) is returned exactly once.
- Create agent principal
Create a named account-level agent identity for execution-side auditing and policy.
- Create collection
Create a collection in the workspace.
- Create environment
Create an environment with variables. Variables may reference existing vault entries (vault://local/<name>) but LLM provider credentials cannot be set over A2A.
- Create execution client
Create an OAuth client scoped to collections in this workspace. The secret is returned exactly once.
- Create item
Create a folder or request (HTTP/GraphQL/WebSocket/gRPC/MCP) in a collection.
- Delete collection
Delete a collection and everything in it.
- Delete environment
Delete an environment.
- Delete item
Delete an item (and its children).
- Export Postman collection
Export a collection as Postman v2.1 JSON.
- Generate a collection from a URL
Discover an API and generate a persisted, authenticated collection wired to credential references (never plaintext secrets). Same pipeline as the REST generate endpoint.
- Get an assistant run
Current state, transcript, plan and pending question of a run started by this principal's owner.
- Get collection
Full collection detail: items tree, variables, scripts.
- Get collection policy
Read the policy document governing broker calls to a collection.
- Get global variables
List the workspace's global variables.
- Get item
Fetch one item with its request definition and children.
- Get workspace
Summary of the workspace this token manages.
- Import Postman collection
Import a Postman v2.1 collection JSON into the workspace.
- List agent principals
List the account's agent principals. Principals are account-level identities (not workspace-scoped), so this spans the owner's whole account.
- List collections
List the collections in the workspace.
- List environments
List the workspace's environments.
- List execution clients
List account-level OAuth clients for the remote MCP execution surface (no secrets returned).
- List pending approvals
List approvals awaiting a human decision. Deciding them is human-only.
- List upstream OAuth grant references
Metadata for existing upstream OAuth grants (names + oauth://<name> references, provider, scopes, status). Secrets and tokens are never returned; grants are created, connected and deleted by a human in the UI.
- List vault entry references
Metadata for existing vault entries (names + vault://local/<name> references). Values are never returned, and secrets can only be created, rotated or deleted by a human in the UI.
- Move item
Re-parent and/or re-order an item within its collection.
- Plan an integration from a sentence
Start an assistant run: the free-text wish is decomposed into connector targets and the run pauses on its first question. Returns the run (transcript, plan, pending question). Never returns secrets.
- Probe an API surface
Run the discovery ladder (OpenAPI/GraphQL/MCP/A2A, plus mail and file servers) against a URL and return the normalized operations, connections and auth summary. Reads only — persists nothing.
- Query the audit trail
Recent broker/A2A audit entries for this account.
- Set collection policy
Set the policy document (hardDeny / requireApproval / behavior rules) for a collection.
- Set global variables
Replace the workspace's global variables.
- Update collection
Update name/description/auth/default environment/scripts.
- Update environment
Rename an environment and/or replace its variables. Any stored LLM credential config is preserved untouched.
- Update item
Update an item's name, request definition and scripts.