ClicheFactory Document Intelligence
PYPI · CLICHEFACTORY-MCP · SCANNED SEP 21
Extract structured JSON from PDFs, images, DOCX, XLSX, CSV, EML attachments, and DSPy pipelines.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
- 4 of 58 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 95 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability64
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1000 tokens (~333/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management90
- Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the ClicheFactory Document Intelligence MCP server?
ClicheFactory Document Intelligence runs locally as a PyPI package, launched with uvx clichefactory-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · clichefactory-mcp
claude mcp add clichefactory-clichefactory-mcp -- uvx clichefactory-mcp
{
"mcpServers": {
"clichefactory-clichefactory-mcp": {
"command": "uvx",
"args": [
"clichefactory-mcp"
]
}
}
} {
"servers": {
"clichefactory-clichefactory-mcp": {
"command": "uvx",
"args": [
"clichefactory-mcp"
]
}
}
} codex mcp add clichefactory-clichefactory-mcp -- uvx clichefactory-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"clichefactory-clichefactory-mcp": {
"type": "local",
"command": [
"uvx",
"clichefactory-mcp"
],
"enabled": true
}
}
} openclaw mcp add clichefactory-clichefactory-mcp --command uvx --arg clichefactory-mcp
mcp_servers:
clichefactory-clichefactory-mcp:
command: "uvx"
args: ["clichefactory-mcp"] {
"McpServers": {
"clichefactory-clichefactory-mcp": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"clichefactory-mcp"
]
}
}
} assistant mcp add clichefactory-clichefactory-mcp -t stdio -c uvx -a clichefactory-mcp
{
"mcpServers": {
"clichefactory-clichefactory-mcp": {
"command": "uvx",
"args": [
"clichefactory-mcp"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 21 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 19 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Sept 26 −3
- Stability: pass → 0.80 functional
- 17 Sept 26 0
- Stability: 0.97 → pass security
- 16 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 11 Sept 26 −3
- Stability: pass → 0.80 functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Sept 2026 · Analysed pypi/clichefactory-mcp@0.1.8
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 58 packages
| Packages resolved | 58 |
|---|---|
| Stale | 3 |
| No linked repository | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
doctor ~76
Check ClicheFactory configuration, dependencies, and system binaries. Returns a diagnostic report showing: - Config file status and API key / model settings - Installed Python dependencies (core + local mode) - System binaries (tesseract, pandoc, LibreOffice) Call this tool first when extraction fails, or to verify the setup is correct.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
extract ~502
Extract structured data from a document using a JSON schema. Takes a document file (PDF, image, DOCX, XLSX, CSV, EML, etc.) and a JSON schema describing the fields to extract. Returns the extracted data as JSON. If extraction fails or returns a validation error, try: 1. Switching mode (e.g. mode="service" if local failed, or vice versa). 2. Using to_markdown first to inspect the document, then adjusting the schema. 3. Using extraction_mode="fast" for simpler documents. Args: file: Absolute path to the document file. schema: Either an absolute file path to a JSON schema, or an inline JSON schema object. Example inline schema: {"type": "object", "properties": {"invoice_number": {"type": "string"}, "total": {"type": "number"}}} mode: Execution mode — "local" (BYOK, runs on user's machine) or "service" (ClicheFactory cloud). Defaults to config file setting. extraction_mode: Extraction strategy. Options: - omit for standard OCR + LLM extraction (most reliable). - "fast" — send raw bytes to a multimodal LLM, skipping OCR (faster). - "trained" — use a trained pipeline artifact (service only, needs artifact_id). - "robust" — two-stage extract + verify (service only). - "robust-trained" — trained extract + verify (service only, needs artifact_id). artifact_id: Trained pipeline artifact ID from ClicheFactory / Emio. Required when extraction_mode is "trained" or "robust-trained". model: LLM model override (e.g. "gemini/gemini-3-flash-preview", "openai/gpt-4o"). model_api_key: API key for the model override. ocr_model: Separate model for OCR/VLM tasks (optional, defaults to main model). ocr_api_key: API key for the OCR model. Returns: JSON string with the extracted data matching the provided schema.
| Name | Type | Req | Description |
|---|---|---|---|
| artifact_id | – | – | – |
| extraction_mode | – | – | – |
| file | string | yes | – |
| mode | – | – | – |
| model | – | – | – |
| model_api_key | – | – | – |
| ocr_api_key | – | – | – |
| ocr_model | – | – | – |
| schema | – | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
to_markdown ~272
Convert a document to markdown text. Takes any supported document (PDF, image, DOCX, XLSX, CSV, EML, etc.) and returns its content as readable markdown. Use this to inspect a document before extraction, or when extract fails and you need to see the content to build a better schema. Args: file: Absolute path to the document file. mode: Client mode — "local" or "service". Defaults to config file setting. conversion_mode: Conversion mode (service mode only). Options: - omit for standard OCR + LLM conversion (most reliable). - "fast" — send raw bytes to a multimodal LLM, skipping OCR (faster). model: LLM model override (e.g. "gemini/gemini-3-flash-preview"). model_api_key: API key for the model override. ocr_model: Separate model for OCR/VLM tasks. ocr_api_key: API key for the OCR model. Returns: The document content as markdown text.
| Name | Type | Req | Description |
|---|---|---|---|
| conversion_mode | – | – | – |
| file | string | yes | – |
| mode | – | – | – |
| model | – | – | – |
| model_api_key | – | – | – |
| ocr_api_key | – | – | – |
| ocr_model | – | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
What is the ClicheFactory Document Intelligence MCP server?
ClicheFactory Document Intelligence is an MCP server listed in the public MCP registry as io.github.ClicheFactory/clichefactory-mcp. Extract structured JSON from PDFs, images, DOCX, XLSX, CSV, EML attachments, and DSPy pipelines. This page covers its PyPI package (clichefactory-mcp).
Is the ClicheFactory Document Intelligence MCP server safe to use?
ClicheFactory Document Intelligence scores 79 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the ClicheFactory Document Intelligence MCP server expose?
ClicheFactory Document Intelligence exposes 3 tools: extract, to_markdown, doctor. Their descriptions and schemas cost roughly 850 tokens of context every time the server is loaded.
Is the ClicheFactory Document Intelligence MCP server still maintained?
ClicheFactory Document Intelligence is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the ClicheFactory Document Intelligence MCP server under?
ClicheFactory Document Intelligence declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.