Koskamo

doc2json MCP

An official MCP server that allows AI agents to parse PDFs, images, and text documents into structured, typed JSON using custom or predefined schemas. It supports features like citations, Excel/CSV export, and schema management, mirroring the functionality of the vendor's REST API.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

doc2json MCP logo, by Manoon LabsVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by Manoon Labs
You need:Create a key on API KeysSend it on every REST and MCP call, as a bearer token or in an x-api-key header
MCP endpoint (Streamable HTTP)
https://doc2json.manoonlabs.com/mcp
Vendor documentation

What you can do with it

  • Extract invoice details from PDFs into JSON
  • Parse receipt images to get merchant and total
  • Convert bank statements to structured data
  • Extract data from forms using custom schemas

Source and maintenance

Vendor evidenceRegistry 1.0.0

Protocol and capabilities

Server
doc2json 0.1.0
MCP protocol
2025-06-18
Tools
6 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Tools

6 advertised

whoami
Advertised by the server during the last successful anonymous check.

Return the workspace and token for the bearer credential, and the credits left this month.

whoami input schema
{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
parse_document
Advertised by the server during the last successful anonymous check.

Extract invoice fields from a PDF, PNG, JPEG, or text file sent as base64 in file_base64, or from plain text sent in text (10 MB and 10 pages on Free, 25 MB and 50 pages on paid). 1 credit per page; an image is 1 page; text is 1 credit per 3,000 characters. Nothing is stored. Send exactly one of file_base64 or text. The result has status and values. Set citations to true to also get, for each value, the page, the printed text, and a box where it was read.

parse_document input schema
{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "The document as plain text, for example a pasted invoice or email. 1 credit per 3,000 characters (started), at least 1. At most 30,000 characters on Free and 150,000 on paid plans. The text is not stored. Send this or file_base64, not both."
    },
    "schema": {
      "oneOf": [
        {
          "type": "string",
          "pattern": "^[a-z0-9_-]+$",
          "maxLength": 80,
          "minLength": 1,
          "description": "Lowercase letters, digits, underscores, and hyphens. No spaces."
        },
        {
          "type": "object",
          "description": "A schema is {\"type\":\"object\",\"properties\":{...}}. Each property is {\"type\":T} where T is one of any, null, boolean, string, number, date, array, object. An optional description, at most 400 characters, tells the model how to read that field. An optional required array lists the keys that must be present. A date is a string yyyy-mm-dd. An array adds \"items\" (one node). An object adds \"properties\" and may add \"required\". At most 4 levels below the root, 100 keys, and 16384 bytes."
        }
      ],
      "description": "The name of a schema saved in this workspace, or a literal schema object. A schema is {\"type\":\"object\",\"properties\":{...}}. Each property is {\"type\":T} where T is one of any, null, boolean, string, number, date, array, object. An optional description, at most 400 characters, tells the model how to read that field. An optional required array lists the keys that must be present. A date is a string yyyy-mm-dd. An array adds \"items\" (one node). An object adds \"properties\" and may add \"required\". At most 4 levels below the root, 100 keys, and 16384 bytes."
    },
    "citations": {
      "type": "boolean",
      "description": "When true, the result also has citations: for each value's path, the page, the printed text it was read from, a box [x0, y0, x1, y1] on the page (0 to 1 from the top left), and a status saying whether the text was found in the document. Same credits. Default false."
    },
    "file_base64": {
      "type": "string",
      "description": "Base64-encoded PDF, PNG, JPEG, or UTF-8 text file (.txt, .md, .csv, .eml). At most 10 MB and 10 pages on Free, 25 MB and 50 pages on paid plans. Each page costs 1 credit; an image is 1 page; text is 1 credit per 3,000 characters. The bytes are not stored. Send this or text, not both."
    }
  },
  "additionalProperties": false
}
list_schemas
Advertised by the server during the last successful anonymous check.

List the extraction schemas saved in this workspace.

list_schemas input schema
{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
get_schema
Advertised by the server during the last successful anonymous check.

Read one saved extraction schema by name.

get_schema input schema
{
  "type": "object",
  "required": [
    "name"
  ],
  "properties": {
    "name": {
      "type": "string",
      "pattern": "^[a-z0-9_-]+$",
      "maxLength": 80,
      "minLength": 1,
      "description": "Lowercase letters, digits, underscores, and hyphens. No spaces."
    }
  },
  "additionalProperties": false
}
create_schema
Advertised by the server during the last successful anonymous check.

Save a named extraction schema in this workspace. A schema is {"type":"object","properties":{...}}. Each property is {"type":T} where T is one of any, null, boolean, string, number, date, array, object. An optional description, at most 400 characters, tells the model how to read that field. An optional required array lists the keys that must be present. A date is a string yyyy-mm-dd. An array adds "items" (one node). An object adds "properties" and may add "required". At most 4 levels below the root, 100 keys, and 16384 bytes.

create_schema input schema
{
  "type": "object",
  "required": [
    "name",
    "schema"
  ],
  "properties": {
    "name": {
      "type": "string",
      "pattern": "^[a-z0-9_-]+$",
      "maxLength": 80,
      "minLength": 1,
      "description": "Lowercase letters, digits, underscores, and hyphens. No spaces."
    },
    "schema": {
      "type": "object",
      "description": "A schema is {\"type\":\"object\",\"properties\":{...}}. Each property is {\"type\":T} where T is one of any, null, boolean, string, number, date, array, object. An optional description, at most 400 characters, tells the model how to read that field. An optional required array lists the keys that must be present. A date is a string yyyy-mm-dd. An array adds \"items\" (one node). An object adds \"properties\" and may add \"required\". At most 4 levels below the root, 100 keys, and 16384 bytes."
    }
  },
  "additionalProperties": false
}
update_schema
Advertised by the server during the last successful anonymous check.

Rename a saved schema, replace its definition, or both. A schema is {"type":"object","properties":{...}}. Each property is {"type":T} where T is one of any, null, boolean, string, number, date, array, object. An optional description, at most 400 characters, tells the model how to read that field. An optional required array lists the keys that must be present. A date is a string yyyy-mm-dd. An array adds "items" (one node). An object adds "properties" and may add "required". At most 4 levels below the root, 100 keys, and 16384 bytes.

update_schema input schema
{
  "type": "object",
  "required": [
    "name"
  ],
  "properties": {
    "name": {
      "type": "string",
      "pattern": "^[a-z0-9_-]+$",
      "maxLength": 80,
      "minLength": 1,
      "description": "The current name."
    },
    "schema": {
      "type": "object",
      "description": "A schema is {\"type\":\"object\",\"properties\":{...}}. Each property is {\"type\":T} where T is one of any, null, boolean, string, number, date, array, object. An optional description, at most 400 characters, tells the model how to read that field. An optional required array lists the keys that must be present. A date is a string yyyy-mm-dd. An array adds \"items\" (one node). An object adds \"properties\" and may add \"required\". At most 4 levels below the root, 100 keys, and 16384 bytes."
    },
    "newName": {
      "type": "string",
      "pattern": "^[a-z0-9_-]+$",
      "maxLength": 80,
      "minLength": 1,
      "description": "Lowercase letters, digits, underscores, and hyphens. No spaces."
    }
  },
  "additionalProperties": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
1571 ms
95th percentile latency
1571 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 1571 ms · metadata changed · 6 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http doc2json-mcp https://doc2json.manoonlabs.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add doc2json-mcp --url https://doc2json.manoonlabs.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable doc2json-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "doc2json-mcp": {
      "url": "https://doc2json.manoonlabs.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "doc2json-mcp": {
      "type": "streamableHttp",
      "url": "https://doc2json.manoonlabs.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start doc2json-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "doc2json-mcp": {
      "type": "http",
      "url": "https://doc2json.manoonlabs.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http doc2json-mcp https://doc2json.manoonlabs.com/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "doc2json-mcp": {
      "url": "https://doc2json.manoonlabs.com/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "doc2json-mcp": {
      "serverUrl": "https://doc2json.manoonlabs.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like doc2json MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Do you run doc2json MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing