ocr-mcp-server@1.0.0
VERIFIED· not startedPublisher claims: "Unified OCR MCP Server - PaddleOCR / Hunyuan / GLM-4V via Model Context Protocol" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
GLM_API_KEYHUNYUAN_API_TOKENPADDLEOCR_API_TOKENConfiguration, not credentials: GLM_NEED_LAYOUT_VIS, GLM_RETURN_CROP_IMAGES, HUNYUAN_MODEL, HUNYUAN_PDF_DPI, HUNYUAN_PROMPT_JSON, HUNYUAN_PROMPT_MARKDOWN, OCR_DEFAULT_PROVIDER, OCR_OUTPUT_FORMAT, OCR_TIMEOUT, PADDLEOCR_API_URL, PADDLEOCR_CHART_RECOGNITION, PADDLEOCR_DOC_ORIENTATION, PADDLEOCR_DOC_UNWARPING, PADDLEOCR_MAX_POLL_TIME, PADDLEOCR_MODEL, PADDLEOCR_POLL_INTERVAL- Where it talks to
- no vendor host named in the codeAlso aistudio-app.com, moark.com, bigmodel.cn — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names aistudio-app.com, moark.com, bigmodel.cn as well as its own vendor. The guard injects GLM_API_KEY, HUNYUAN_API_TOKEN, PADDLEOCR_API_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-13 and scored it 93/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
ocr-mcp-server --transport streamable-http --port 8000Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.f"[ocr-mcp-server] Starting HTTP server on {args.host}:{args.port}",Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
No advisories in OSV for ocr-mcp-server@1.0.0 as of 22 h ago. This is the package itself, not its dependencies.