AI & ML41 toolsPaste one API key
Parallel integration for AI agents
Parallel offers a Task API for automated, structured web research, transforming natural language queries into precise, schema-compliant outputs.
Use it from your agent
One ClawLink account serves every agent you run. Pick the guide for yours, or connect Parallel once and call the same tools from all of them.
Parallel for OpenClawInstall, pair, connect, first prompt
Parallel for Hermes AgentInstall, pair, connect, first promptMCPClaude Code, Cursor, any MCP clientCLI login or the remote MCP serverSetup
Connect Parallel through ClawLink's hosted setup.
- Auth: Paste one API key. The credential stays on the ClawLink server; your agent holds only a ClawLink key you can revoke.
- Where: the ClawLink dashboard, or ask your agent to connect it.
What your agent can do
Parallel exposes 41 tools through ClawLink. The 30 most used are listed here; your agent sees all of them.
| Tool | What it does | Kind |
|---|---|---|
parallel_create_chat_completions | Get realtime chat completions from Parallel AI | Write |
parallel_extract | Extract relevant content from specific web URLs | Read |
parallel_extract_web_content | Extract excerpts or full content from known web URLs with Parallel's current stable Extract API | Read |
parallel_fetch_task_group_runs | Retrieve task runs from a Task Group as a resumable stream | Read |
parallel_generate_grounded_response | Generate a synchronous answer grounded in live web research with URL citation annotations | Read |
parallel_get_find_all_run_result | Fetch the final (or latest available) FindAll candidates and result payload for a run | Read |
parallel_get_find_all_run_schema | Retrieve the schema configuration of a FindAll run by findall_id | Read |
parallel_get_monitor | Retrieve a monitor's configuration and runtime state by ID using Parallel's current stable | Read |
parallel_get_task_group | Retrieve a current stable-API snapshot of a Task Group's aggregate run counts and status | Read |
parallel_ingest_find_all_run | Transform a natural language search objective into a structured FindAll specification | Read |
parallel_list_current_monitors | List monitors from Parallel's current stable Monitor API, newest first, with optional type and | Read |
parallel_list_monitor_events | List events for a monitor from up to the last 300 event groups | Read |
parallel_list_monitors | List active monitors for the user | Read |
parallel_list_task_group_runs | Collect Task Group runs from the current stable API's resumable event stream, optionally | Read |
parallel_list_task_run_events | Collect progress and state events from a Task Run using the current stable API | Read |
parallel_retrieve_event_group | Retrieve an event group for a monitor | Read |
parallel_retrieve_find_all_run_status | Retrieve status and metadata for a FindAll run by findall_id | Read |
parallel_retrieve_memory | Retrieve relevant memories ranked against a query, or recent memories when the query is empty | Read |
parallel_retrieve_monitor | Retrieve a specific monitor by ID | Read |
parallel_retrieve_task_group | Retrieve details of a specific task group | Read |
parallel_retrieve_task_group_run | Retrieve run status by run_id for a task group | Read |
parallel_retrieve_task_run | Retrieve run status by run_id | Read |
parallel_retrieve_task_run_input | Retrieve the input data of a specific task run by run_id | Read |
parallel_retrieve_task_run_result | Retrieve the result of a task run by run_id, blocking until the run completes | Read |
parallel_search | Perform parallel semantic search | Read |
parallel_search_web | Search the web with Parallel's current stable Search API and return ranked results with | Read |
parallel_stream_find_all_events | Stream events from a FindAll run | Read |
parallel_stream_task_group_events | Stream events for a Task Group | Read |
parallel_stream_task_run_events | Stream events for a Task Run | Read |
parallel_suggest_task | Suggest tasks based on user intent | Read |
