MinerU
NPM · MINERU-MCP · SCANNED SEP 20
MinerU document parsing API — PDFs, images, DOCX, PPTX with OCR and batch processing.
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 Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 34 of 108 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency97
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to linxule/mineru-mcp). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 3 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability71
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1014 tokens (~126/item across 8 items; 8 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 Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "mineru_merge_slices" implies "merge" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 8 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 MinerU MCP server?
MinerU runs locally as an npm package, launched with npx -y mineru-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · mineru-mcp
claude mcp add linxule-mineru -- npx -y mineru-mcp
{
"mcpServers": {
"linxule-mineru": {
"command": "npx",
"args": [
"-y",
"mineru-mcp"
]
}
}
} {
"servers": {
"linxule-mineru": {
"command": "npx",
"args": [
"-y",
"mineru-mcp"
]
}
}
} codex mcp add linxule-mineru -- npx -y mineru-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"linxule-mineru": {
"type": "local",
"command": [
"npx",
"-y",
"mineru-mcp"
],
"enabled": true
}
}
} openclaw mcp add linxule-mineru --command npx --arg -y --arg mineru-mcp
mcp_servers:
linxule-mineru:
command: "npx"
args: ["-y", "mineru-mcp"] {
"McpServers": {
"linxule-mineru": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"mineru-mcp"
]
}
}
} assistant mcp add linxule-mineru -t stdio -c npx -a -y mineru-mcp
{
"mcpServers": {
"linxule-mineru": {
"command": "npx",
"args": [
"-y",
"mineru-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.
- 20 Sept 26 +1
- Security disclosure: fail → unverified ▼ functional
- 18 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.
- 17 Sept 26 +12
- Malware scan: unverified → pass ▲ security
- Stability: pass → 0.80 functional
- 16 Sept 26 −16
- Malware scan: pass → unverified ▼ security
- Stability: 0.97 → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Stability: 0.97 → pass security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Security disclosure: fail → unverified ▼ functional
- Schema quality: pass → fail ▼ functional
- First check of Schema quality: unverified functional
- Destructive annotations: pass → 0 functional
- Package version: 1.1.6 → 1.2.0 functional
- 15 Sept 26 +15
- Malware scan: unverified → pass ▲ security
- 14 Sept 26 −13
- Stability: 0.90 → unverified ▼ security
- Malware scan: pass → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- CVE-2026-82562 no longer affects this package ▲ security
- CVE-2026-82417 no longer affects this package ▲ security
- Known CVEs: fail → pass ▲ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- First check of Schema quality: unverified functional
- Package version: 1.1.4 → 1.1.6 functional
- 13 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.
- 11 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.
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 20 Sept 2026 · Analysed npm/mineru-mcp@1.2.0
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | linxule/mineru-mcp |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/linxule/mineru-mcp/.github/workflows/publish-mcp.yml@refs/tags/v1.2.0 |
| Rekor log index | 2862985207 |
| Predicate type | https://slsa.dev/provenance/v1 |
| Subject digest | sha512:3f9721c27ac0e137fed78f47ddc94265a750b504e1419e9b9620b3c8d86bb4abfc9d2f55cd85db86227cb510148fe441429bb4c9a34c5d92fbc439d04 |
Background: How many MCP packages publish verified provenance →
Dependencies 108 packages
| Packages resolved | 108 |
|---|---|
| Stale | 34 |
| 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 →
mineru_batch ~137
Parse multiple URLs in one batch (max 200). Preferred over mineru_upload_batch — faster and more reliable. Use public URLs (arXiv, SSRN, publisher sites) when available.
| Name | Type | Req | Description |
|---|---|---|---|
| formats | array | – | Extra export formats |
| formula | boolean | – | Formula recognition |
| language | string | – | Language code: ch, en, etc |
| model | string | – | pipeline=fast, vlm=90% accuracy |
| ocr | boolean | – | Enable OCR (pipeline only) |
| table | boolean | – | Table recognition |
| urls | – | yes | Array of document URLs, or a single URL string |
No output schema declared.
No examples provided.
mineru_batch_status ~65
Get batch results. Supports pagination for large batches.
| Name | Type | Req | Description |
|---|---|---|---|
| batch_id | string | yes | Batch ID from mineru_batch |
| format | string | – | Output format |
| limit | number | – | Max results to return |
| offset | number | – | Skip first N results |
No output schema declared.
No examples provided.
mineru_download_results ~95
Download batch results and extract named paper folders. Each folder contains {name}.md, {name}_content.json (structured TOC), and images/. Output includes parsed title — verify it matches the expected paper.
| Name | Type | Req | Description |
|---|---|---|---|
| batch_id | string | yes | Batch ID from mineru_upload_batch or mineru_batch |
| output_dir | string | yes | Directory to save markdown files |
| overwrite | boolean | – | Overwrite existing files |
No output schema declared.
No examples provided.
mineru_merge_slices ~130
Stitch the slices of a mineru_parse_long batch into one {name}/{name}.md (+ {name}_content.json with page_idx re-based to the whole document, + images/). Slices are ordered by their page range; each is marked with an HTML comment. Waits for nothing — if any slice is still processing, it reports and you re-run later.
| Name | Type | Req | Description |
|---|---|---|---|
| batch_id | string | yes | Batch ID from mineru_parse_long |
| output_dir | string | yes | Directory to write the merged document folder into |
| overwrite | boolean | – | Overwrite an existing merged folder |
No output schema declared.
No examples provided.
mineru_parse ~132
Parse a document URL. Returns task_id to check status.
| Name | Type | Req | Description |
|---|---|---|---|
| formats | array | – | Extra export formats |
| formula | boolean | – | Formula recognition |
| language | string | – | Language code: ch, en, etc |
| model | string | – | pipeline=fast, vlm=90% accuracy |
| ocr | boolean | – | Enable OCR (pipeline only) |
| pages | string | – | Page range: 1-10,15 or 2--2 |
| table | boolean | – | Table recognition |
| url | string | yes | Document URL (PDF, DOC, PPT, images) |
No output schema declared.
No examples provided.
mineru_parse_long ~257
Parse a document LONGER than 200 pages (MinerU's per-file cap) by submitting it as one batch of ≤200-page slices with page_ranges. Give total_pages (from `mdls -name kMDItemNumberOfPages`, `pdfinfo`, or the viewer) — it is auto-detected only for local files on macOS. Returns a batch_id; poll with mineru_batch_status, then stitch with mineru_merge_slices. Files ≤200 pages: use mineru_parse instead.
| Name | Type | Req | Description |
|---|---|---|---|
| file | string | – | Absolute local file path (uploaded once per slice — slow for big files) |
| formula | boolean | – | Formula recognition |
| language | string | – | Language code: ch, en, etc |
| model | string | – | pipeline=fast, vlm=90% accuracy |
| name | string | – | Output name for the merged result (default: from URL/file name) |
| ocr | boolean | – | Enable OCR (pipeline only) |
| slice_size | integer | – | Pages per slice (≤200) |
| table | boolean | – | Table recognition |
| total_pages | integer | – | Total page count of the document |
| url | string | – | Public document URL (preferred) |
No output schema declared.
No examples provided.
mineru_status ~42
Check task progress. Returns download URL when done.
| Name | Type | Req | Description |
|---|---|---|---|
| format | string | – | Output format |
| task_id | string | yes | Task ID from mineru_parse |
No output schema declared.
No examples provided.
mineru_upload_batch ~156
Upload local files for batch parsing. SLOW: uploads can take minutes and may timeout. Prefer mineru_batch with public URLs (arXiv, SSRN, publisher sites) when available — it's faster and more reliable. Only use this for files not available online.
| Name | Type | Req | Description |
|---|---|---|---|
| directory | string | – | Directory path containing PDF/DOC/PPT files |
| files | – | – | Array of absolute file paths, or a single path string |
| formats | array | – | Extra export formats |
| formula | boolean | – | Formula recognition |
| language | string | – | Language code: ch, en, etc |
| model | string | – | pipeline=fast, vlm=90% accuracy |
| table | boolean | – | Table recognition |
No output schema declared.
No examples provided.
What is the MinerU MCP server?
MinerU is an MCP server listed in the public MCP registry as io.github.linxule/mineru. MinerU document parsing API, PDFs, images, DOCX, PPTX with OCR and batch processing. This page covers its npm package (mineru-mcp).
Is the MinerU MCP server safe to use?
MinerU scores 91 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 MinerU MCP server expose?
MinerU exposes 8 tools: mineru_parse, mineru_status, mineru_batch, mineru_batch_status, mineru_upload_batch, and 3 more. Their descriptions and schemas cost roughly 1,014 tokens of context every time the server is loaded.
Is the MinerU MCP server still maintained?
MinerU is still listed as active in the MCP registry. We last reached this channel on 20 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 MinerU MCP server under?
MinerU declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.