ClicheFactory Document Intelligence runs on your own machine — the client starts it, so there is no endpoint to ping. 120 installs a week from pypi. Last commit 17 Jun 2026.
Extract structured JSON from PDFs, images, DOCX, XLSX, CSV, EML attachments, and DSPy pipelines.
We read the source, 5 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
__import__(module)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add clichefactory-mcp -- uvx clichefactory-mcp
{
"mcpServers": {
"clichefactory-mcp": {
"command": "uvx",
"args": [
"clichefactory-mcp"
]
}
}
}
[mcp_servers.clichefactory-mcp]
command = "uvx"
args = ["clichefactory-mcp"]
{
"mcpServers": {
"clichefactory-mcp": {
"command": "uvx",
"args": [
"clichefactory-mcp"
]
}
}
}
{
"servers": {
"clichefactory-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"clichefactory-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
CLICHEFACTORY_API_KEY (ClicheFactory API key for service mode), CLICHEFACTORY_API_URL (Optional ClicheFactory API base URL override), LLM_MODEL_NAME (Model name for local mode, for example gemini/gemini-3-flash-preview), LLM_API_KEY (LLM provider API key for local mode), OCR_MODEL_NAME (Optional OCR/VLM model override), OCR_API_KEY (Optional OCR/VLM provider API key).
Extract structured, schema-validated data from PDFs, scans, images, spreadsheets, and forms.
Sector impact of Indian financial events as structured JSON, from a hosted API. Needs an API key.
Extract every table from PDFs and scans to Excel, CSV and JSON.
Any URL to clean markdown/JSON; PDF, XLSX, CSV, DOCX to text and tables. Free tier for agents.
Any URL to clean markdown/JSON; PDF, XLSX, CSV, DOCX to text and tables. Free tier for agents.
Turn rows into bar, line, pie and scatter chart images plus an optional PDF or HTML report.
Read and analyze local documents (PDF, Excel, CSV, Word, PowerPoint, images). No API keys needed.
Real .docx and .xlsx files from structured data, with automatic Hebrew/Arabic RTL.
Answers built from our own checks of this server.