About AIDataParser
AIDataParser is a hosted data-extraction API that converts PDFs, images, and raw text into JSON matching a JSON Schema. It is for applications that need structured document data, and also supports schema inference and JSON validation.
Key features
- 01Extract JSON from PDFs and images
- 02Convert raw text to structured JSON
- 03Infer JSON Schemas from samples
- 04Validate JSON against a schema
- 05Use built-in schema templates
- 06Check remaining API key credits
Use cases
- 01Extract fields from invoices or receipts
- 02Structure data from documents such as resumes
- 03Generate reusable schemas from sample data
- 04Validate JSON before submission
MCP support
The hosted MCP server uses Streamable HTTP to provide document and text parsing, schema inference, and validation tools.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://aidataparser.com/v1/mcpclaude mcp add --transport http shibley-aidataparser https://aidataparser.com/v1/mcp{"mcpServers":{"shibley-aidataparser":{"type":"http","url":"https://aidataparser.com/v1/mcp"}}}Open in Cursor{"servers":{"shibley-aidataparser":{"type":"http","url":"https://aidataparser.com/v1/mcp"}}}Open in VS Code{"mcpServers":{"shibley-aidataparser":{"type":"http","url":"https://aidataparser.com/v1/mcp"}}}{"mcpServers":{"shibley-aidataparser":{"serverUrl":"https://aidataparser.com/v1/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
9| Parameter | Type | Required | Description |
|---|---|---|---|
| text | string | Yes | The raw text to extract structured data from, up to 4000 characters. Send a representative excerpt rather than a whole corpus. |
| schema | object | No | Optional JSON Schema describing the exact output shape you want. When provided, the returned `data` conforms to it. |
| schema_id | string | No | Optional named template to use instead of a hand-written schema, e.g. "invoice", "receipt", "resume". Call list_schemas for the full set. Ignored when `schema` is provided. |
| instructions | string | No | Optional natural-language guidance for what to extract. |
Details
From the project READMEAIDataParser MCP server
The official Model Context Protocol registry record for AIDataParser — a credit-based data-extraction API that turns PDFs, images and messy text into schema-guaranteed JSON.
There is no server code in this repo. The MCP server is hosted: it lives at
https://aidataparser.com/v1/mcp and speaks JSON-RPC 2.0 over Streamable HTTP.
This repo holds the server.json that is the source of our record in
registry.modelcontextprotocol.io,
the canonical upstream every downstream MCP catalog syncs from.
Add it to your client
{
"mcpServers": {
"aidataparser": {
"type": "http",
"url": "https://aidataparser.com/v1/mcp",
"headers": { "Authorization": "Bearer adp_live_..." }
}
}
}
Try it before you sign up. try_parse runs a real extraction with no key,
no email and no account — up to 4,000 characters of text, 3 calls per day. Add
the server without the headers block and call it:
{ "name": "try_parse", "arguments": { "text": "INVOICE #1042 ... Total due $1,240.00", "schema_id": "invoice" } }
When you want more, get a key (50 free credits, no card) — over MCP with the
create_api_key tool, or:
curl -X POST https://aidataparser.com/v1/keys \
-H 'Content-Type: application/json' \
-d '{"email":"[email protected]"}'
Tools
| Tool | Cost | What it does |
|---|---|---|
try_parse | free, no key | Real extraction on ≤4,000 chars of text, 3/day — see the output before signing up |
create_api_key | free, no key | An email → a live adp_live_ key with 50 free credits |
parse_document | 1 credit | PDF or image (url or base64) → JSON matching your schema |
parse_text | 1 credit | Raw/messy text → JSON matching your schema |
infer_schema | 1 credit | One sample → a reusable JSON Schema |
validate | free, no key | Check a JSON value against a schema |
check_credits | free | Credits remaining on the key |
list_schemas | free, no key | Built-in templates (invoice, receipt, resume, …) |
Credit packs: https://aidataparser.com/pricing
Publishing
.github/workflows/publish-mcp.yml publishes on a push to main using GitHub
OIDC — no secrets. Bump version in server.json to cut a release; a push that
does not change the version is a no-op.
Before it publishes, the workflow runs two gates:
npm test— static checks onserver.json(validate-server-json.mjs). Each rule maps to a real failure from a sibling repo, e.g. the registry's 100-char description cap that 422'daisotools-mcp-serverv0.1.0.npm run check:remote— a liveinitialize+tools/listhandshake against the URL about to be advertised. A registry record pointing at a dead endpoint is worse than no record.
Both are runnable locally.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.