Prefect MCP connector for AI agents

Tools your workflow orchestration agent reaches for on Prefect, scoped per user.

CALL ANY TOOL

15 read-only tools for workflow orchestration: inspect flows, deployments, flow and task runs, logs, work pools, automations, and events, plus Prefect docs search.

prefectmcp_docs_get_release_notes

Docs get release notes

Get authoritative, structured release notes for a Prefect OSS release. Accepts "latest" or an exact version and returns the release title, date, Markdown notes, and source URL.

Parameters

Name

Type

Required

Description

version

string

Optional

'latest' for the latest stable Prefect OSS release, or an exact version such as '3.7.8'. Default: `latest`.

prefectmcp_docs_search_prefect

Docs search prefect

prefectmcp_get_automations

Get automations

prefectmcp_get_dashboard

Get dashboard

prefectmcp_get_deployments

Get deployments

prefectmcp_get_flow_run_logs

Get flow run logs

prefectmcp_get_flow_runs

Get flow runs

prefectmcp_get_flows

Get flows

prefectmcp_get_identity

Get identity

prefectmcp_get_object_schema

Get object schema

prefectmcp_get_task_runs

Get task runs

prefectmcp_get_work_pools

Get work pools

prefectmcp_list_authorized_workspaces

List authorized workspaces

prefectmcp_orientation

Orientation

prefectmcp_read_events

Read events

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Prefect MCP tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["prefectmcp"], toolNames: [
    "prefectmcp_get_flow_runs",
    "prefectmcp_get_flow_run_logs",
    "prefectmcp_get_deployments"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Why did last night's nightly-etl flow run fail?" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["prefectmcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Why did last night's nightly-etl flow run fail?" }],
  tools,
});

// Execute the tool call with the user's vaulted Prefect token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["prefectmcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Why did last night's nightly-etl flow run fail?" }],
  tools,
});

// Tool call runs with the user's vaulted Prefect token
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["prefectmcp"] }, pageSize: 100,
});

const agent = new Agent({
  name: "devops_agent",
  model: "gemini-2.5-pro",
  instruction: "Prefect MCP tools scoped to this user",
  tools,
});

await agent.run("Why did last night's nightly-etl flow run fail?");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Prefect MCP tool. Click to copy, paste into your agent, done.

Runs and failures

Copy the prompt

Copied

List failed flow runs from the last 24 hours.

Copy the prompt

Copied

Show the logs for this flow run.

Copy the prompt

Copied

Which task runs in this flow run are still pending?

Deployments and infrastructure

Copy the prompt

Copied

List the deployments for this flow.

Copy the prompt

Copied

List the work pools in this workspace.

Copy the prompt

Copied

Give me a dashboard overview of this Prefect instance.

Events and docs

Copy the prompt

Copied

Read the events from the last hour.

Copy the prompt

Copied

List the automations configured in this workspace.

Copy the prompt

Copied

Search the Prefect docs for how retries work.

SEE HOW AUTH WORKS

Each user signs in to Prefect once; Scalekit stores and refreshes their tokens. Tokens stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Prefect 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

Store

Their

Prefect 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

Resolve

When your agent calls a

Prefect 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

Audit

Every

Prefect 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

See the same per-user auth pattern across other developer and monitoring connectors.

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.

Engineering Teams

Engineering standup agent

Pulls commits from GitHub and GitLab, tracks issue movement in Jira, and posts a per-engineer standup brief to Slack. Each engineer's activity is read on their own delegated OAuth.

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.

Engineering Teams

Auto release notes agent

Reads merged GitHub PRs, groups them into structured release notes, publishes the page to Notion, and announces the release in Slack. Every call runs on the engineer's own delegated OAuth.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Prefect token looks fine in a demo. In production every run and log read looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Prefect today. Ten connectors 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 Prefect as the user or as a shared key?

As the user. Each user signs in to Prefect once, and Scalekit stores and refreshes their tokens. Audit logs attribute every run and log read to that user, not a shared service account.

Where is the Prefect OAuth token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Prefect?

Yes. Filter by tool name in listScopedTools to expose only what you want. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Prefect 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 trigger or change Prefect runs?

No. All 15 Prefect MCP tools are read-only: flows, deployments, flow and task runs, logs, work pools, automations, events, and Prefect docs. Access covers only the Prefect Cloud workspaces the user selected during OAuth consent.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit