Parallel AI Task MCP

Live

API KEY

ORCHESTRATION

AI

Parallel AI Task MCP lets your agent dispatch multiple sub-tasks concurrently and collect results in a single context. Your orchestration agent can fan out research, analysis, or data retrieval across parallel workers and merge outputs.

  • Acts as the user: Access and write actions stay tied to the Parallel AI Task MCP account that authorized the agent.
  • Credentials stay vaulted: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: Permissions enforced. 90-day audit trail.
Parallel AI Task MCP
agent · Acme Q3
Run
Research the top 5 competitor pricing pages and summarize each in parallel.
S
parallel_tasks_run
4.2s
Orchestration agent
All 5 tasks completed in 4.2s. Competitor A: usage-based, $0.02/call. Competitor B: seat-based, $49/seat. Competitor C: tiered, free to $299/mo. Competitor D: enterprise-only. Competitor E: open source, self-hosted.
Sources: 5 competitor pages, parallel
parallelaitaskmcpmcp
5 tasks
18:29
Message Claude...

Tools your orchestration agent reaches for on Parallel AI Task MCP, scoped per user.

CALL ANY TOOL
Fan out tasks in parallel, poll individual results, cancel running tasks, and retrieve batch outputs.
parallelaitaskmcp_get_status
Get status
Lightweight status check for a Deep Research or Task Group run. Use this for polling instead of getResultMarkdown to avoid fetching large payloads unnecessarily. When to use: - Check whether a task run or task group has completed - Poll for progress on a running task When NOT to use: - Task is already complete and you need the results : use parallelaitaskmcp_get_result_markdown instead Do NOT poll automatically unless the user explicitly instructs you to.
Parameters
Name
Type
Required
Description
taskRunOrGroupId
string
Required
Task run identifier (trun_*) or task group identifier (tgrp_*) to check status for.
parallelaitaskmcp_create_task_group
Create task group
parallelaitaskmcp_get_result_markdown
Get result markdown
parallelaitaskmcp_create_deep_research
Create deep research
Build your Agent
Drop the toolkit in, point it at the user, and your orchestration agent can use Parallel AI Task MCP from the first run.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["parallelaitaskmcp"], toolNames: ["parallel_tasks_run", "parallel_task_get", "parallel_tasks_list"] },
pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
name: t.tool.definition.name,
description: t.tool.definition.description,
schema: z.object({}).passthrough(),
func: async (args) => {
const { data } = await sk.tools.executeTool({
toolName: t.tool.definition.name,
identifier: "user_123",
params: args,
});
return JSON.stringify(data);
},
}));

const agent = createReactAgent({ llm, tools: lcTools });
import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["parallelaitaskmcp"], toolNames: ["parallel_tasks_run", "parallel_task_get", "parallel_tasks_list"] },
pageSize: 100,
});

const llmTools = tools.map((t) => ({
type: "function",
function: {
name: t.tool.definition.name,
description: t.tool.definition.description,
parameters: t.tool.definition.input_schema,
},
}));

const resp = await openai.responses.create({
model: "gpt-4o", input: prompt, tools: llmTools,
});
import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["parallelaitaskmcp"], toolNames: ["parallel_tasks_run", "parallel_task_get", "parallel_tasks_list"] },
pageSize: 100,
});

const llmTools = tools.map((t) => ({
name: t.tool.definition.name,
description: t.tool.definition.description,
input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
model: "claude-sonnet-4-6", max_tokens: 1024,
tools: llmTools,
messages: [{ role: "user", content: prompt }],
});
import { Agent } from "@google/adk/agents";
import {
MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
connectionParams: new StreamableHTTPConnectionParams({
url: "https://mcp.scalekit.com/parallelaitaskmcp",
headers: { Authorization: `Bearer ${userScopedToken}` },
}),
});

const agent = new Agent({
name: "agent", model: "gemini-2.0-flash",
tools: await toolset.getTools(),
});
Try these prompts
Paste any prompt into your agent to start using Parallel AI Task MCP.
Parallel execution
Copy the prompt
Copied
Run 5 research tasks in parallel for [topic].
Copy the prompt
Copied
Fan out [query] against [list of sources] simultaneously.
Copy the prompt
Copied
Get results for task batch [ids].
Copy the prompt
Copied
Cancel all running tasks.
Status & monitoring
Copy the prompt
Copied
List all running tasks right now.
Copy the prompt
Copied
Get status for task [id].
Copy the prompt
Copied
How many tasks completed in the last hour?
Copy the prompt
Copied
Which tasks failed today?
Orchestration
Copy the prompt
Copied
Run competitive analysis on [domain list] in parallel.
Copy the prompt
Copied
Research [topic] from 10 sources simultaneously.
Copy the prompt
Copied
Summarize each of these [URLs] concurrently.
Copy the prompt
Copied
Batch-enrich [company list] with data in parallel.
SEE HOW AUTH WORKS
Users authorize Parallel AI Task MCP once. Their credentials stay vaulted, every call is checked, and every action is logged.
1
Authorize
Your user connects
Parallel AI Task MCP
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Parallel AI Task MCP
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Parallel AI Task MCP
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Parallel AI Task MCP
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
Same per-user auth pattern across other orchestration agents and MCP connectors. Working code, live demos, fork what fits.
Engineering Teams
Slack triage
Polls Slack for new messages, classifies bugs and support requests with a LangGraph router, files GitHub issues or Zendesk tickets, and confirms in the thread.
Support and Ops Teams
Support ticket automation agent
Fetches new Zendesk tickets, drafts a reply from Notion knowledge base articles, digests what it cannot answer to Slack, and archives the rest, acting as the support agent rather than a shared API key.
Engineering Teams
DevOps assistant agent
Polls GitHub for failing checks and stale PRs, opens Linear issues for the ones that need work, and posts a daily digest to Slack. It acts as the engineer, not a shared service account.
Support and Ops Teams
Email-to-calendar agent
Reads scheduling intent out of Gmail threads, resolves the times everyone actually has free, and creates the event on the user's own Google Calendar. No shared service account.
Test other agents
Same per-user auth pattern across other orchestration agents and MCP connectors. Working code, live demos, fork what fits.
ENGINEERING
DevOps assistant agent
Poll GitHub for failing checks and stale pull requests, open Linear issues for the ones that need work, and digest to Slack.
ENGINEERING
Slack triage agent
Classify new Slack messages as bugs or support requests, file the GitHub issue or Zendesk ticket, and reply in the thread.
SUPPORT
Support ticket automation (Google ADK)
Fetch, annotate, and archive Zendesk tickets with Notion context, digesting anything it cannot answer to Slack.
OPS
Email-to-calendar scheduling agent
Read scheduling intent out of Gmail threads, resolve mutual free time, and create the Google Calendar event.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.
// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Parallel AI Task MCP today. Others tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access Parallel AI Task MCP as the user or as a shared key?
As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.
Where is the Parallel AI Task MCP api key stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.
Can I limit what the agent is allowed to do in Parallel AI Task MCP?
Yes. Pass a tool name filter to listScopedTools so the orchestration agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Parallel AI Task MCP.
What happens when a user revokes Parallel AI Task MCP access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.
Can the agent share task results across users in the same workspace?
Only within the same API key scope. Task results are namespaced per key. Results from one user's key are inaccessible to another unless explicitly shared via your application layer.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""parallelaitaskmcp"": {
""url"": ""https://mcp.scalekit.com/parallelaitaskmcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.parallelaitaskmcp]
url = ""https://mcp.scalekit.com/parallelaitaskmcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""parallelaitaskmcp"": {
""url"": ""https://mcp.scalekit.com/parallelaitaskmcp"",
""type"": ""http""
}
}
}