AgentQL MCP integration for AI agents.
Connect AI agents to AgentQL through 4 structured actions, including get usage, create browser session, and list session usage. Review authentication, inputs…
- ACTION CONTRACTS
- 4
- AUTHENTICATION
- API key
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the AgentQL integration exposes
The AgentQL Agent App exposes 4 provider-backed actions for ai, developer tools, and data work. Its current contract lets an authorized agent get agentql account and api key usage counters for the current billing cycle and lifetime totals, create an agentql tetra remote browser session and return the session, cdp, and base urls, and list agentql tetra session telemetry entries with optional filters and pagination controls. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.
A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.
For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected AgentQL account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real AgentQL capabilities.
Showing 4 of 4 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_usageREADGet AgentQL account and API key usage counters for the current billing cycle and lifetime totals.
create_browser_sessionWRITECreate an AgentQL Tetra remote browser session and return the session, CDP, and base URLs.
INPUTS: browser_ua_preset / browser_profile / shutdown_mode / inactivity_timeout_seconds / proxy
list_session_usageREADList AgentQL Tetra session telemetry entries with optional filters and pagination controls.
INPUTS: sub_user_id / session_id / start_after / end_before / updated_after
query_dataREADQuery a webpage with AgentQL and return the extracted structured data plus AgentQL metadata.
INPUTS: query / prompt / url / html / params
INPUT CONTRACTS
Know what the action needs before it runs.
create_browser_session
browser_ua_presetOPTIONAL- Browser user agent preset used when creating a Tetra browser session.
browser_profileOPTIONAL- Browser profile used by AgentQL for the request or session.
shutdown_modeOPTIONAL- How AgentQL should stop the browser session after disconnect.
inactivity_timeout_secondsOPTIONAL- Inactivity timeout in seconds before AgentQL closes the session.
proxyOPTIONAL- Proxy configuration for AgentQL browser-backed operations.
list_session_usage
sub_user_idOPTIONAL- Only return telemetry entries for this sub-user identifier.
session_idOPTIONAL- Only return telemetry for this session identifier.
start_afterOPTIONAL- Only include sessions that started after this timestamp.
end_beforeOPTIONAL- Only include sessions that ended before this timestamp.
updated_afterOPTIONAL- Only include sessions updated after this timestamp.
query_data
queryOPTIONALpromptOPTIONALurlOPTIONALhtmlOPTIONALparamsOPTIONAL- Optional query execution settings forwarded to AgentQL query-data.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Usage
Get AgentQL account and API key usage counters for the current billing cycle and lifetime totals. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_usageControl Create Browser Session
Create an AgentQL Tetra remote browser session and return the session, CDP, and base URLs. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
create_browser_sessionVerify with List Session Usage
List AgentQL Tetra session telemetry entries with optional filters and pagination controls. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
list_session_usageSAFETY BOUNDARY
Operate AgentQL with explicit limits
- Authorize AgentQL with API key and grant only the provider access required by the selected actions.
- 1 action is change-capable by name. Confirm the target identity and material parameters before allowing a write.
- Do not infer permission from catalog visibility. Workspace policy, connection identity, and upstream authorization still govern execution.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in AgentQL rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the AgentQL task completed successfully.
CONNECTION MODEL
API key
AgentQL API key used with the X-API-Key header. Get it from the AgentQL developer dashboard.
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 3
- WRITE SIGNALS
- 1
- HIGH IMPACT
- 0
- REVIEW SIGNALS
- 0
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by AgentQL.