pdfco-mcp 0.1.0__tar.gz

pdfco_mcp-0.1.0/.github/workflows/release.yml

@@ -0,0 +1,65 @@
+name: release
+
+permissions:
+  contents: write
+  packages: write
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  set-version:
+    runs-on: ubuntu-24.04
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Export tag
+        id: vars
+        run: echo tag=${GITHUB_REF#refs/*/} >> $GITHUB_OUTPUT
+        if: ${{ github.event_name == 'release' }}
+
+      - name: Update project version
+        run: |
+          sed -i "s/^version = \".*\"/version = \"$RELEASE_VERSION\"/" pyproject.toml
+        env:
+          RELEASE_VERSION: ${{ steps.vars.outputs.tag }}
+        if: ${{ github.event_name == 'release' }}
+
+      - name: Upload updated pyproject.toml
+        uses: actions/upload-artifact@v4
+        with:
+          name: pyproject-toml
+          path: pyproject.toml
+
+  publish:
+    runs-on: ubuntu-latest
+    needs: [set-version]
+    steps:
+      - name: Check out
+        uses: actions/checkout@v4
+
+      - name: Set up the environment
+        uses: ./.github/actions/setup-python-env
+
+      - name: Download updated pyproject.toml
+        uses: actions/download-artifact@v4
+        with:
+          name: pyproject-toml
+
+      - name: Build package
+        run: uv build
+
+      - name: Publish package
+        run: uv publish
+        env:
+          UV_PUBLISH_TOKEN: ${{ secrets.PYPI_TOKEN }}
+
+      - name: Upload dists to release
+        uses: svenstaro/upload-release-action@v2
+        with:
+            repo_token: ${{ secrets.GITHUB_TOKEN }}
+            file: dist/*
+            file_glob: true
+            tag: ${{ github.ref }}
+            overwrite: true

pdfco_mcp-0.1.0/.gitignore

@@ -0,0 +1,14 @@
+# Python-generated files
+__pycache__/
+*.py[oc]
+build/
+dist/
+wheels/
+*.egg-info
+
+# Virtual environments
+.venv
+.env
+.cursor
+sandbox
+.DS_Store

pdfco_mcp-0.1.0/.python-version

@@ -0,0 +1 @@
+3.12

pdfco_mcp-0.1.0/PKG-INFO

@@ -0,0 +1,33 @@
+Metadata-Version: 2.4
+Name: pdfco-mcp
+Version: 0.1.0
+Summary: Add your description here
+Requires-Python: >=3.12
+Requires-Dist: httpx>=0.28.1
+Requires-Dist: langchain-community>=0.3.21
+Requires-Dist: langchain[google-genai]>=0.3.23
+Requires-Dist: langgraph>=0.3.30
+Requires-Dist: mcp[cli]>=1.6.0
+Description-Content-Type: text/markdown
+
+# PDF.co MCP
+
+#### Sample `.cursor/mcp.json` for test in cursor
+```json
+{
+  "mcpServers": {
+    "pdfco": {
+      "command": "uv",
+      "args": [
+        "--directory",
+        "/path/to/pdfco-mcp",
+        "run",
+        "main.py"
+      ],
+      "env": {
+        "X_API_KEY": "YOUR_TEST_KEY"
+      }
+    }
+  }
+}
+```

pdfco_mcp-0.1.0/README.md

@@ -0,0 +1,21 @@
+# PDF.co MCP
+
+#### Sample `.cursor/mcp.json` for test in cursor
+```json
+{
+  "mcpServers": {
+    "pdfco": {
+      "command": "uv",
+      "args": [
+        "--directory",
+        "/path/to/pdfco-mcp",
+        "run",
+        "main.py"
+      ],
+      "env": {
+        "X_API_KEY": "YOUR_TEST_KEY"
+      }
+    }
+  }
+}
+```

pdfco_mcp-0.1.0/pdfco/mcp/__init__.py

@@ -0,0 +1,8 @@
+from pdfco.mcp.server import mcp
+from pdfco.mcp.tools.apis import conversion, job, file, modification, form, search, searchable, security, document, extraction, editing
+    
+def main():
+    mcp.run(transport="stdio")
+
+if __name__ == "__main__":
+    main()

pdfco_mcp-0.1.0/pdfco/mcp/models.py

@@ -0,0 +1,68 @@
+from pydantic import BaseModel, Field
+from typing import Any
+
+class BaseResponse(BaseModel):
+    status: str
+    content: Any
+    credits_used: int | None = None
+    credits_remaining: int | None = None
+    tips: str | None = None
+
+class ConversionParams(BaseModel):
+    url: str = Field(description="URL to the source file. Supports publicly accessible links including Google Drive, Dropbox, PDF.co Built-In Files Storage. Use 'upload_file' tool to upload local files.", default="")
+    httpusername: str = Field(description="HTTP auth user name if required to access source url. (Optional)", default="")
+    httppassword: str = Field(description="HTTP auth password if required to access source url. (Optional)", default="")
+    pages: str = Field(description="Comma-separated page indices (e.g., '0, 1, 2-' or '1, 3-7'). Use '!' for inverted page numbers (e.g., '!0' for last page). Processes all pages if None. (Optional)", default="")
+    unwrap: bool = Field(description="Unwrap lines into a single line within table cells when lineGrouping is enabled. Must be true or false. (Optional)", default=False)
+    rect: str = Field(description="Defines coordinates for extraction (e.g., '51.8,114.8,235.5,204.0'). (Optional)", default="")
+    lang: str = Field(description="Language for OCR for scanned documents. Default is 'eng'. See PDF.co docs for supported languages. (Optional, Default: 'eng')", default="eng")
+    line_grouping: str = Field(description="Enables line grouping within table cells when set to '1'. (Optional)", default="0")
+    password: str = Field(description="Password of the PDF file. (Optional)", default="")
+    name: str = Field(description="File name for the generated output. (Optional)", default="")
+    autosize: bool = Field(description="Controls automatic page sizing. If true, page dimensions adjust to content. If false, uses worksheet’s page setup. (Optional)", default=False)
+
+    html: str = Field(description="Input HTML code to be converted. To convert the link to a PDF use the /pdf/convert/from/url endpoint instead.", default="")
+    templateId: str = Field(description="Set to the ID of your HTML template. You can find and copy the ID from HTML to PDF Templates.", default="")
+    templateData: str = Field(description="Set it to a string with input JSON data (recommended) or CSV data.", default="")
+    margins: str = Field(description="Set to CSS style margins like 10px, 5mm, 5in for all sides or 5px 5px 5px 5px (the order of margins is top, right, bottom, left). (Optional)", default="")
+    paperSize: str = Field(description="A4 is set by default. Can be Letter, Legal, Tabloid, Ledger, A0, A1, A2, A3, A4, A5, A6 or a custom size. Custom size can be set in px (pixels), mm or in (inches) with width and height separated by space like this: 200 300, 200px 300px, 200mm 300mm, 20cm 30cm or 6in 8in. (Optional)", default="")
+    orientation: str = Field(description="Set to Portrait or Landscape. Portrait is set by default. (Optional)", default="")
+    printBackground: bool = Field(description="true by default. Set to false to disable printing of background. (Optional)", default=True)
+    mediaType: str = Field(description="Uses print by default. Set to screen to convert HTML as it appears in a browser or print to convert as it appears for printing or none to set none as mediaType for CSS styles. (Optional)", default="")
+    DoNotWaitFullLoad: bool = Field(description="false by default. Set to true to skip waiting for full load (like full video load etc. that may affect the total conversion time). (Optional)", default=False)
+    header: str = Field(description="User definable HTML for the header to be applied on every page header. (Optional)", default="")
+    footer: str = Field(description="User definable HTML for the footer to be applied on every page footer. (Optional)", default="")
+
+    worksheetIndex: str = Field(description="Index of the worksheet to convert. (Optional)", default="")
+
+    def parse_payload(self, async_mode: bool = True):
+        payload = {
+            "async": async_mode,
+        }
+        if self.url: payload["url"] = self.url
+        if self.httpusername: payload["httpusername"] = self.httpusername
+        if self.httppassword: payload["httppassword"] = self.httppassword
+        if self.pages: payload["pages"] = self.pages
+        if self.unwrap: payload["unwrap"] = self.unwrap
+        if self.rect: payload["rect"] = self.rect
+        if self.lang: payload["lang"] = self.lang
+        if self.line_grouping: payload["lineGrouping"] = self.line_grouping
+        if self.password: payload["password"] = self.password
+        if self.name: payload["name"] = self.name
+        if self.autosize: payload["autosize"] = self.autosize
+        
+        if self.html: payload["html"] = self.html
+        if self.templateId: payload["templateId"] = self.templateId
+        if self.templateData: payload["templateData"] = self.templateData
+        if self.margins: payload["margins"] = self.margins
+        if self.paperSize: payload["paperSize"] = self.paperSize
+        if self.orientation: payload["orientation"] = self.orientation
+        if self.printBackground: payload["printBackground"] = self.printBackground
+        if self.mediaType: payload["mediaType"] = self.mediaType
+        if self.DoNotWaitFullLoad: payload["DoNotWaitFullLoad"] = self.DoNotWaitFullLoad
+        if self.header: payload["header"] = self.header
+        if self.footer: payload["footer"] = self.footer
+        
+        if self.worksheetIndex: payload["worksheetIndex"] = self.worksheetIndex
+        
+        return payload

pdfco_mcp-0.1.0/pdfco/mcp/server.py

@@ -0,0 +1,3 @@
+from mcp.server.fastmcp import FastMCP
+
+mcp = FastMCP("pdfco")

pdfco_mcp-0.1.0/pdfco/mcp/services/client.py

@@ -0,0 +1,49 @@
+from contextlib import asynccontextmanager
+from httpx import AsyncClient
+import os, sys
+from typing import AsyncGenerator
+import importlib.metadata
+
+__BASE_URL = "https://api.pdf.co"
+X_API_KEY = os.getenv("X_API_KEY")  
+
+__version__ = importlib.metadata.version('pdfco-mcp')
+print(f"pdfco-mcp version: {__version__}", file=sys.stderr)
+
+@asynccontextmanager
+async def PDFCoClient() -> AsyncGenerator[AsyncClient, None]:
+    if not X_API_KEY:
+        raise ValueError("""X_API_KEY is not set. Please set X_API_KEY in the environment variables in your MCP server. 
+        To get the API key please sign up at https://pdf.co and you can get the API key from the dashboard.
+        ex) .cursor/mcp.json
+        ```json
+        {
+            "mcpServers": {
+                "pdfco": {
+                    "command": "uv",
+                    "args": [
+                        "--directory",
+                        "/Users/outstandingboy/workspace/pdfco-mcp",
+                        "run",
+                        "pdfco-mcp"
+                    ],
+                    "env": {
+                        "X_API_KEY": "YOUR_API_KEY"
+                    }
+                }
+            }
+        }
+        ```
+        """)
+    
+    client = AsyncClient(
+            base_url=__BASE_URL,
+            headers={
+                "x-api-key": X_API_KEY,
+                "User-Agent": f"pdfco-mcp/{__version__}",
+            },
+        )
+    try:
+        yield client
+    finally:
+        await client.aclose()

pdfco_mcp-0.1.0/pdfco/mcp/services/pdf.py

@@ -0,0 +1,95 @@
+import sys
+from pdfco.mcp.models import BaseResponse, ConversionParams
+from pdfco.mcp.services.client import PDFCoClient
+
+async def convert_to(_from: str, _to: str, params: ConversionParams) -> BaseResponse:
+    return await request(f'{_from}/convert/to/{_to}', params)
+
+async def convert_from(_to: str, _from: str, params: ConversionParams) -> BaseResponse:
+    return await request(f'{_to}/convert/from/{_from}', params)
+
+async def merge_pdf(params: ConversionParams) -> BaseResponse:
+    return await request(f'pdf/merge2', params)
+
+async def split_pdf(params: ConversionParams) -> BaseResponse:
+    return await request(f'pdf/split', params)
+
+async def get_pdf_form_fields_info(params: ConversionParams) -> BaseResponse:
+    return await request('pdf/info/fields', params)
+
+async def fill_pdf_form_fields(params: ConversionParams, fields: list = None, annotations: list = None) -> BaseResponse:
+    custom_payload = {}
+    if fields:
+        custom_payload["fields"] = fields
+    if annotations:
+        custom_payload["annotations"] = annotations
+    return await request('pdf/edit/add', params, custom_payload=custom_payload)
+
+async def pdf_add(params: ConversionParams, **kwargs) -> BaseResponse:
+    """General PDF Add function that supports all PDF Add API parameters"""
+    custom_payload = {}
+    
+    # Add all supported parameters
+    for key, value in kwargs.items():
+        if value is not None and value != "":
+            custom_payload[key] = value
+    
+    return await request('pdf/edit/add', params, custom_payload=custom_payload)
+
+async def find_text_in_pdf(params: ConversionParams, search_string: str, regex_search: bool = False, word_matching_mode: str = None) -> BaseResponse:
+    custom_payload = {
+        "searchString": search_string,
+        "regexSearch": regex_search
+    }
+    if word_matching_mode:
+        custom_payload["wordMatchingMode"] = word_matching_mode
+    return await request('pdf/find', params, custom_payload=custom_payload)
+
+async def find_table_in_pdf(params: ConversionParams) -> BaseResponse:
+    return await request('pdf/find/table', params)
+
+async def make_pdf_searchable(params: ConversionParams) -> BaseResponse:
+    return await request('pdf/makesearchable', params)
+
+async def make_pdf_unsearchable(params: ConversionParams) -> BaseResponse:
+    return await request('pdf/makeunsearchable', params)
+
+async def get_pdf_info(params: ConversionParams) -> BaseResponse:
+    return await request('pdf/info', params)
+
+async def add_pdf_password(params: ConversionParams, **kwargs) -> BaseResponse:
+    return await request('pdf/security/add', params, custom_payload=kwargs)
+
+async def remove_pdf_password(params: ConversionParams) -> BaseResponse:
+    return await request('pdf/security/remove', params)
+
+async def parse_invoice(params: ConversionParams) -> BaseResponse:
+    return await request('ai-invoice-parser', params)
+
+async def extract_pdf_attachments(params: ConversionParams) -> BaseResponse:
+    return await request('pdf/attachments/extract', params)
+
+async def request(endpoint: str, params: ConversionParams, custom_payload: dict = None) -> BaseResponse:
+    payload = params.parse_payload(async_mode=True)
+    if custom_payload:
+        payload.update(custom_payload)
+        
+    try:
+        async with PDFCoClient() as client:
+            url = f"/v1/{endpoint}"
+            print(f"Requesting {url} with payload {payload}", file=sys.stderr)
+            response = await client.post(url, json=payload)
+            print(f"response: {response}", file=sys.stderr)
+            json_data = response.json()
+            return BaseResponse(
+                status="working",
+                content=json_data,
+                credits_used=json_data.get("credits"),
+                credits_remaining=json_data.get("remainingCredits"),
+                tips=f"You **should** use the 'wait_job_completion' tool to wait for the job [{json_data.get('jobId')}] to complete if a jobId is present.",
+            )
+    except Exception as e:
+        return BaseResponse(
+            status="error",
+            content=f'{type(e)}: {[arg for arg in e.args if arg]}',
+        )