Airparser MCP connector for AI agents

CALL ANY TOOL

Document parsing end to end: create inboxes, upload files, read structured output, and manage extraction schemas.

airparsermcp_list_inboxes

List inboxes

List the active Airparser inboxes available to the authenticated user, the starting point for any upload or schema call.

Parameters

Name

Type

Required

Description

—

No parameters required

airparsermcp_create_inbox

Create an inbox

airparsermcp_upload_document_sync

Upload and parse

airparsermcp_get_document

Get parsed document

airparsermcp_list_documents

List documents

airparsermcp_generate_schema_from_document

Propose a schema

airparsermcp_get_extraction_schema

Read the schema

airparsermcp_update_extraction_schema

Update the schema

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);

// Airparser tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["airparsermcp"], toolNames: [
    "airparsermcp_upload_document_sync",
    "airparsermcp_get_document",
    "airparsermcp_list_inboxes"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Parse this invoice and extract the vendor and total." }] });

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: ["airparsermcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "List the documents parsed in the Invoices inbox this week." }],
  tools,
});

// Execute the tool call with the user's vaulted Airparser credential
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: ["airparsermcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Generate a schema proposal from the latest document in the Contracts inbox." }],
  tools,
});

// Tool call runs with the user's vaulted Airparser credential
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: ["airparsermcp"] }, pageSize: 100,
});

const agent = new Agent({
  name: "airparser_document_agent",
  model: "gemini-2.5-pro",
  instruction: "Parse documents for the signed-in user.",
  tools,
});

await agent.run("Create a new inbox for purchase orders.");

Try these prompts

Copy any prompt into your agent. Each maps directly to an Airparser tool. Click to copy, paste into your agent, done.

Parse documents

Copy the prompt

Copied

Upload this invoice to the Invoices inbox and return the parsed fields.

Copy the prompt

Copied

Get the parsed JSON for the latest document in the Contracts inbox.

Copy the prompt

Copied

List the last 10 documents parsed in the Receipts inbox.

Manage inboxes

Copy the prompt

Copied

List my active Airparser inboxes.

Copy the prompt

Copied

Create a new inbox for purchase orders.

Copy the prompt

Copied

Show the extraction schema configured for the Invoices inbox.

Tune extraction schemas

Copy the prompt

Copied

Generate a schema proposal from the last document in the Invoices inbox.

Copy the prompt

Copied

Update the Contracts inbox schema to add a renewal_date field.

Copy the prompt

Copied

Convert this JSON schema into the native Airparser format and save it.

SEE HOW AUTH WORKS

Your users connect once. Their Airparser credentials stay vaulted, every call is scope-checked, and every action is logged.

1

Authorize

Your user connects

Airparser 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

Airparser 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

Airparser 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

Airparser 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 document 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 identity, scope enforcement, and audit. Connectors follow.

01.

Shared tokens break per-user analytics

A shared Airparser key looks fine in a demo. In production every upload and schema edit looks like one service account, and you cannot tell who parsed a contract or changed an inbox. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared key
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Airparser 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 Airparser as the user or through a shared key?

As the user. Scalekit resolves the API key of the person who triggered the agent at request time, so every upload and schema change in your audit trail is attributed to a real user, not a shared service account.

Where is the Airparser API key stored?

In an AES-256 encrypted vault with per-tenant namespacing. Keys are resolved at request time, never enter LLM context, and can be rotated or revoked from one dashboard.

Can I limit what the agent does in Airparser?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example upload and read tools without schema updates or post-processing writes. Scalekit also enforces scope checks before every API call.

What happens when a user revokes access?

The credential is invalidated at the next tool call. The call fails closed, other users' connections are unaffected, and the revocation is logged in the audit chain.

Can the agent change my post-processing Python code?

Only if you expose it. Airparser splits testing from writing: test_postprocessing_code runs code against a parsed document without saving, while save_postprocessing_code persists it. Filter out the save and enable tools in listScopedTools to keep the agent in a dry-run lane.

Airparser MCP

Tools your document agent reaches for on Airparser, scoped per user.