Connect AI agents to the Airparser MCP server

Vendor MCP

The Airparser MCP connector routes your AI agent's tool calls to Airparser's own MCP server through Scalekit. Each user signs in to Airparser once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 17 tools.

Tools: 17
What they doRead · write · destructive: 8 · 9 · 08 read9 write0 destructive
Users sign in with: OAuth
OAuth app: Your own Airparser MCP server app

Setup

Install the SDK
- Node.js
- Python
Terminal window
npm install @scalekit-sdk/node dotenv
Terminal window
pip install scalekit-sdk-python python-dotenv
Set your credentials
Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.
.env
```
SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
SCALEKIT_CLIENT_ID=<your-client-id>
SCALEKIT_CLIENT_SECRET=<your-client-secret>
```
Create the Airparser MCP connection
In AgentKit > Connections, create an Airparser MCP connection and copy its redirect URI. The name you give it is the connection_name your code passes. See Configure connections.
Register an OAuth app
Airparser MCP server connections use your own OAuth app. Register one with Airparser MCP server and add the redirect URI you copied.
Then enter the app's Client ID and Client Secret on the Airparser MCP connection.

Authorize a user and make your first call

Node.js
Python

1
import { ScalekitClient } from '@scalekit-sdk/node'
2
import 'dotenv/config'
3
import { createInterface } from 'node:readline/promises'
4

5
const scalekit = new ScalekitClient(
6
  process.env.SCALEKIT_ENVIRONMENT_URL,
7
  process.env.SCALEKIT_CLIENT_ID,
8
  process.env.SCALEKIT_CLIENT_SECRET,
9
)
10
const actions = scalekit.actions
11

12
const connector = 'airparsermcp'
13
const identifier = 'user_123'
14

15
// Generate an authorization link for the user
16
const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
17
console.log('Authorize Airparser MCP:', link)
18
const rl = createInterface({ input: process.stdin, output: process.stdout })
19
await rl.question('Press Enter after authorizing...')
20
rl.close()
21

22
// Make your first call
23
const result = await actions.executeTool({
24
  connector,
25
  identifier,
26
  toolName: 'airparsermcp_get_extraction_schema_format_guide',
27
  toolInput: {},
28
})
29
console.log(result)

npx tsx quickstart.mts

1
import os
2
from scalekit import ScalekitClient
3
from dotenv import load_dotenv
4
load_dotenv()
5

6
scalekit_client = ScalekitClient(
7
    env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),
8
    client_id=os.getenv("SCALEKIT_CLIENT_ID"),
9
    client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
10
)
11
actions = scalekit_client.actions
12

13
connection_name = "airparsermcp"
14
identifier = "user_123"
15

16
# Generate an authorization link for the user
17
link_response = actions.get_authorization_link(
18
    connection_name=connection_name,
19
    identifier=identifier,
20
)
21
print("Authorize Airparser MCP:", link_response.link)
22
input("Press Enter after authorizing...")
23

24
# Make your first call
25
result = actions.execute_tool(
26
    tool_input={},
27
    tool_name="airparsermcp_get_extraction_schema_format_guide",
28
    connection_name=connection_name,
29
    identifier=identifier,
30
)
31
print(result)

python quickstart.py

Each user signs in once. See Authorize a user for the full flow and statuses.

Tools

Pass the exact name to execute_tool

Try in Playground Request a tool

airparsermcp_get_documentGet one Airparser document with parsed JSON for the authenticated user.Read-only
Get Document
Get one Airparser document with parsed JSON for the authenticated user.
Inputs
document_idstringrequired
Airparser document id.
airparsermcp_get_extraction_schemaGet the current extraction schema configured for an Airparser inbox.Read-only
Get Extraction Schema
Get the current extraction schema configured for an Airparser inbox.
Inputs
inbox_idstringrequired
Airparser inbox id.
airparsermcp_get_extraction_schema_format_guideGet a compact guide to the native Airparser extraction schema format, including field types and examples.Read-only
Get Extraction Schema Format Guide
Get a compact guide to the native Airparser extraction schema format, including field types and examples.
Inputs
This tool takes no inputs.
airparsermcp_get_inboxGet a single Airparser inbox, including extraction schema details.Read-only
Get Inbox
Get a single Airparser inbox, including extraction schema details.
Inputs
inbox_idstringrequired
Airparser inbox id.
airparsermcp_get_postprocessingGet the current Airparser post-processing configuration for an inbox, including whether it is enabled and the saved Python code.Read-only
Get Post-Processing Configuration
Get the current Airparser post-processing configuration for an inbox, including whether it is enabled and the saved Python code.
Inputs
inbox_idstringrequired
Airparser inbox id.
airparsermcp_get_postprocessing_runtime_rulesGet the runtime constraints and allowed imports for Airparser post-processing Python code.Read-only
Get Post-Processing Runtime Rules
Get the runtime constraints and allowed imports for Airparser post-processing Python code.
Inputs
This tool takes no inputs.
airparsermcp_list_documentsList documents inside an Airparser inbox, including recent parsed results and pagination metadata.Read-only
List Documents
List documents inside an Airparser inbox, including recent parsed results and pagination metadata.
Inputs
inbox_idstringrequired
Airparser inbox id.
fromstring
Start date filter in YYYY-MM-DD format.
pageinteger
1-based page number for pagination.
tostring
End date filter in YYYY-MM-DD format.
airparsermcp_list_inboxesList active Airparser inboxes available to the authenticated user.Read-only
List Inboxes
List active Airparser inboxes available to the authenticated user.
Inputs
This tool takes no inputs.
airparsermcp_create_inboxCreate a new Airparser inbox with the selected LLM engine.Write
Create Inbox
Create a new Airparser inbox with the selected LLM engine.
Inputs
llm_enginestringrequired
Parsing engine: 'text' for text-based documents, 'vision' for image-based documents.one of textvision
namestringrequired
Human-friendly inbox name.
airparsermcp_generate_schema_from_documentGenerate an Airparser extraction schema proposal from an existing document in an inbox.Write
Generate Schema From Document
Generate an Airparser extraction schema proposal from an existing document in an inbox.
Inputs
document_idstringrequired
Existing document id inside that inbox.
inbox_idstringrequired
Airparser inbox id.
airparsermcp_save_postprocessing_codeSave Airparser post-processing Python code for an inbox without changing whether it is enabled.Write
Save Postprocessing Code
Save Airparser post-processing Python code for an inbox without changing whether it is enabled.
Inputs
codestringrequired
Python function body to save.
inbox_idstringrequired
Airparser inbox id.
airparsermcp_set_postprocessing_enabledEnable or disable the saved Airparser post-processing step for an inbox.Write
Set Post-Processing Enabled
Enable or disable the saved Airparser post-processing step for an inbox.
- Idempotent
Inputs
inbox_idstringrequired
Airparser inbox id.
is_enabledbooleanrequired
Whether post-processing should be enabled.
airparsermcp_test_postprocessing_codeRun Airparser post-processing Python code against an existing parsed document without saving it.Write
Test Post-Processing Code
Run Airparser post-processing Python code against an existing parsed document without saving it.
- Idempotent
Inputs
codestringrequired
Python function body to run inside the restricted Airparser post-processing wrapper.
document_idstringrequired
Parsed Airparser document id.
inbox_idstringrequired
Airparser inbox id.
airparsermcp_update_extraction_schemaCreate or update the extraction schema for an Airparser inbox using the native validated schema format.Write
Update Extraction Schema
Create or update the extraction schema for an Airparser inbox using the native validated schema format.
- Idempotent
Inputs
fieldsarrayrequired
Extraction schema fields in Airparser native format. Each field object must use "name" (not "key") as the field identifier.
inbox_idstringrequired
Airparser inbox id.
airparsermcp_update_extraction_schema_from_json_schemaConvert an OpenAI-style schema description into the native Airparser extraction schema format and save it to an inbox.Write
Update Extraction Schema From JSON Schema
Convert an OpenAI-style schema description into the native Airparser extraction schema format and save it to an inbox.
- Idempotent
Inputs
fieldsarrayrequired
OpenAI-style field definitions to convert. Each item has name, description, type, and optional attributes.
inbox_idstringrequired
Airparser inbox id.
airparsermcp_update_fields_metaEnable or disable per-document output metadata fields for an Airparser inbox.Write
Update Fields Meta
Enable or disable per-document output metadata fields for an Airparser inbox. Only passed fields are changed; omitted fields keep their current value.
- Idempotent
Inputs
fields_metaobjectrequired
Partial set of metadata fields to enable/disable. Optional boolean properties: from, from_name, original_recipient, to, cc, bcc, reply_to, subject, received_at_datetime, received_at_date, received_at_time, attachments_nb, doc_id, doc_url, content_type, content, content_plaintext, content_plaintext_md, download_url, parent_id, parent_data, name, filename, credits, pages, confidence.
inbox_idstringrequired
Airparser inbox id.
airparsermcp_upload_document_syncUpload one document to an Airparser inbox and wait for the parsed result.Write
Upload Document Sync
Upload one document to an Airparser inbox and wait for the parsed result. File content must be base64 encoded.
Inputs
content_base64stringrequired
Base64-encoded file contents.
content_typestringrequired
MIME type of the document.
filenamestringrequired
Original filename including extension.
inbox_idstringrequired
Target Airparser inbox id.
metadataobject
Optional metadata key-value pairs to attach.

Setup

Install the SDK

Set your credentials

Create the Airparser MCP connection

Register an OAuth app

Authorize a user and make your first call

Tools

Call it

Returns

Get Document

Inputs

Get Extraction Schema

Inputs

Get Extraction Schema Format Guide

Inputs

Get Inbox

Inputs

Get Post-Processing Configuration

Inputs

Get Post-Processing Runtime Rules

Inputs

List Documents

Inputs

List Inboxes

Inputs

Create Inbox

Inputs

Generate Schema From Document

Inputs

Save Postprocessing Code

Inputs

Set Post-Processing Enabled

Inputs

Test Post-Processing Code

Inputs

Update Extraction Schema

Inputs

Update Extraction Schema From JSON Schema

Inputs

Update Fields Meta

Inputs

Upload Document Sync

Inputs

Related: other Files & Documents connectors