Pylon MCP connector for AI agents

CALL ANY TOOL

Search accounts, issues, tasks, and projects. Create and update items, upload files, and look up users. Same toolkit, every framework, no auth plumbing.

pylonmcp_get_me

Get current user

Retrieve the currently authenticated Pylon user with role and workspace metadata.

Parameters

Name

Type

Required

Description

—

No parameters required

pylonmcp_search_issues

Search issues and tasks

pylonmcp_get_issue

Get issue

pylonmcp_create_task

Create task

pylonmcp_update_task

Update task

pylonmcp_create_project_from_template

Create project from template

pylonmcp_upload_file

Upload file to account

Build your Agent

Drop the toolkit in, point it at the user, and your agent can search and update Pylon issues, tasks, and projects from the first run.

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: ["pylonmcp"], toolNames: ["pylonmcp_get_me", "pylonmcp_search_issues", "pylonmcp_get_issue"] },
  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: ["pylonmcp"], toolNames: ["pylonmcp_get_me", "pylonmcp_search_issues", "pylonmcp_get_issue"] },
  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: ["pylonmcp"], toolNames: ["pylonmcp_get_me", "pylonmcp_search_issues", "pylonmcp_get_issue"] },
  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/pylonmcp",
    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 working with Pylon from your workflows.

Search & triage

Copy the prompt

Copied

Find all open issues for account [name] from the past week.

Copy the prompt

Copied

Show every task assigned to me with due date this week.

Copy the prompt

Copied

List all unresolved issues tagged [label].

Action & create

Copy the prompt

Copied

Create a follow-up task for issue [id] due Friday.

Copy the prompt

Copied

Spin up a new onboarding project for [account] from the standard template.

Copy the prompt

Copied

Upload [file] to account [name] and tag with [label].

SEE HOW AUTH WORKS

Users authorize Pylon once. Their credentials stay vaulted, every call is checked, and every action is logged.

1

Authorize

Your user connects

Pylon 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

Pylon 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

Pylon 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

Pylon 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 CRM and support connectors.

No items found.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.

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.

Pylon 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 act as the user or a shared key?

As the user. Each Pylon user authorizes once and Scalekit resolves their credential at request time. All edits and assignments are attributed to that user.

Where is the Pylon OAuth token stored?

In Scalekit's AES-256 vault, namespaced per tenant. Refresh is automatic. Tokens never appear in prompts or LLM context.

Can I prevent the agent from deleting tasks?

Yes. Use listScopedTools to allow create_task and update_task without granting delete_task.

What happens when a user revokes Pylon access?

The connection is invalidated on the next tool call. Subsequent requests fail closed with a clear error.

Can the agent combine Pylon issues with Slack messages in one workflow?

Yes. A single agent can read Pylon issues and post Slack updates in the same workflow, each using the same user identity.

Pylon MCP

Tools your agent reaches for on Pylon MCP, scoped per user.