TruePath PDF
NPM · @TRUEPATHPDF/MCP-SERVER · SCANNED SEP 24
Local-only PDF tools for AI — extract text, search, split/merge, render pages. Files never leave.
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 113 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 80 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability78
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1218 tokens (~135/item across 9 items; 9 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 Management83
- Stability observed for 25 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; "merge" 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 9 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 TruePath PDF MCP server?
TruePath PDF runs locally as an npm package, launched with npx -y @truepathpdf/mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @truepathpdf/mcp-server
claude mcp add joytruepath-truepath-pdf-mcp -- npx -y @truepathpdf/mcp-server
{
"mcpServers": {
"joytruepath-truepath-pdf-mcp": {
"command": "npx",
"args": [
"-y",
"@truepathpdf/mcp-server"
]
}
}
} {
"servers": {
"joytruepath-truepath-pdf-mcp": {
"command": "npx",
"args": [
"-y",
"@truepathpdf/mcp-server"
]
}
}
} codex mcp add joytruepath-truepath-pdf-mcp -- npx -y @truepathpdf/mcp-server
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"joytruepath-truepath-pdf-mcp": {
"type": "local",
"command": [
"npx",
"-y",
"@truepathpdf/mcp-server"
],
"enabled": true
}
}
} openclaw mcp add joytruepath-truepath-pdf-mcp --command npx --arg -y --arg @truepathpdf/mcp-server
mcp_servers:
joytruepath-truepath-pdf-mcp:
command: "npx"
args: ["-y", "@truepathpdf/mcp-server"] {
"McpServers": {
"joytruepath-truepath-pdf-mcp": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"@truepathpdf/mcp-server"
]
}
}
} assistant mcp add joytruepath-truepath-pdf-mcp -t stdio -c npx -a -y @truepathpdf/mcp-server
{
"mcpServers": {
"joytruepath-truepath-pdf-mcp": {
"command": "npx",
"args": [
"-y",
"@truepathpdf/mcp-server"
]
}
}
} 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.
- 24 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.
- 23 Sept 26 −3
- Stability: pass → 0.80 functional
- 22 Sept 26 0
- Stability: 0.97 → pass security
- 21 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.
- 19 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.
- 17 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.
- 16 Sept 26 −3
- Stability: pass → 0.80 functional
- 15 Sept 26 0
- Stability: 0.97 → pass security
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 24 Sept 2026 · Analysed npm/@truepathpdf/mcp-server@0.3.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 113 packages
| Packages resolved | 113 |
|---|---|
| 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 →
extract_images Extract embedded images ~131
Pull embedded images out of a PDF and write each as a PNG. Unsupported pixel layouts (e.g. CMYK, palettized) are skipped and reported.
| Name | Type | Req | Description |
|---|---|---|---|
| basename | string | – | Stem for output filenames. Default = source name. Final form: '<stem>-p001-img01.png'. |
| outputDir | string | yes | Directory to write extracted images into. |
| pages | string | – | 1-based page range. Omit for all pages. Format: "1-5" or "1,3,5-7". |
| path | string | yes | Absolute path to the source PDF. |
No output schema declared.
No examples provided.
extract_text Extract text ~104
Extract plain text from a local PDF. Optionally restrict to a page range like "1-5" or "1,3,5-7". Output is split by page with === Page N === markers.
| Name | Type | Req | Description |
|---|---|---|---|
| pages | string | – | Page range (1-based). Examples: "3", "1-5", "1,3,5-7". Omit for all pages. |
| path | string | yes | Absolute path to a PDF on the local filesystem. |
No output schema declared.
No examples provided.
get_info Get PDF info ~54
Return page count, first-page size, encryption status, and embedded metadata (title, author, dates, producer, etc.) for a local PDF.
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | Absolute path to a PDF on the local filesystem. |
No output schema declared.
No examples provided.
merge Merge PDFs ~78
Combine two or more PDFs into one, preserving page order. Outputs to a caller-specified path.
| Name | Type | Req | Description |
|---|---|---|---|
| outputPath | string | yes | Absolute path for the combined output PDF. Its parent directory will be created if missing. |
| paths | array | yes | Two or more absolute PDF paths to combine, in order. The result preserves pages in the order given. |
No output schema declared.
No examples provided.
open_in_truepath Open in TruePath PDF (Mac app) ~162
Hand a local PDF to the TruePath PDF Mac app via its truepath:// URL scheme so the user can finish work in a GUI (annotate, sign, fill forms, redact). The bridge is fire-and-forget — the app handles opening from there. Requires the app installed (https://joytruepath.com/truepath-pdf).
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | Absolute path to the PDF to open in the TruePath PDF Mac app. |
| scheme | string | – | URL scheme of the receiving app. Default "truepath". Set this if you're handing off to a re-branded build of the engine — e.g. "yochenpdf" for the Yochen core build, or whatever urlScheme the destina… |
No output schema declared.
No examples provided.
pages Edit pages (rotate / delete / reorder) ~207
One-pass page editor. Delete pages, rotate specific pages by 90°/180°/270°, and reorder the result — in any combination. Page numbers in `rotate` refer to the SOURCE PDF; `reorder` refers to post-delete positions.
| Name | Type | Req | Description |
|---|---|---|---|
| delete | string | – | Pages to delete, 1-based, comma/range form. Example: "1,3,5-7". Applied BEFORE rotate and reorder. |
| outputPath | string | yes | Absolute path to write the result to. |
| path | string | yes | Absolute path to the source PDF. |
| reorder | array | – | New page order, expressed as 1-based positions in the post-delete output. Example: [3,1,2] puts page 3 first. Must be a permutation of all surviving pages. |
| rotate | array | – | Per-page absolute rotations applied to pages that survive the delete step. Page numbers refer to the SOURCE PDF, not the post-delete one — easier to reason about. |
No output schema declared.
No examples provided.
search Search PDF ~124
Find a substring across the whole PDF. Returns each hit's page, offset within the page, and a snippet of surrounding text. Use for grep-style discovery before extracting full text.
| Name | Type | Req | Description |
|---|---|---|---|
| caseSensitive | boolean | – | Case-sensitive match. Default false. |
| contextChars | integer | – | How many characters of surrounding text to include per hit (default 60). |
| maxHits | integer | – | Cap the number of hits returned (default 200). |
| path | string | yes | Absolute path to a PDF on the local filesystem. |
| query | string | yes | Text to search for. |
No output schema declared.
No examples provided.
split Split PDF ~138
Split a PDF into multiple PDFs by page ranges. Each range becomes one output file written into outputDir.
| Name | Type | Req | Description |
|---|---|---|---|
| basename | string | – | Stem for output filenames. Default = source filename without .pdf. Final names look like '<basename>-1-3.pdf'. |
| outputDir | string | – | Directory to write outputs into. Defaults to the source PDF's directory. |
| path | string | yes | Absolute path to the source PDF. |
| ranges | array | yes | Page ranges to split into separate output PDFs, 1-based. Examples: ["1-3", "4-7", "8"] produces three files. Each range becomes one output PDF. |
No output schema declared.
No examples provided.
to_images Render pages to images ~220
Rasterize PDF pages as PNG or JPG at a chosen DPI. Useful for previews, OCR pipelines, or feeding pages back to a vision model.
| Name | Type | Req | Description |
|---|---|---|---|
| basename | string | – | Stem for output filenames. Default = source filename without .pdf. Final names: '<basename>-001.png' (page number padded to 3 digits). |
| dpi | integer | – | Render resolution. Default 150. PDF native is 72; common values: 96 screen, 150 print preview, 300 print. |
| format | string | – | Output format. Default "png". "jpg" is smaller but lossy. |
| jpgQuality | integer | – | JPEG quality 40-100. Default 85. Ignored for PNG. |
| outputDir | string | yes | Directory to write the rendered images into. |
| pages | string | – | 1-based page range, e.g. "3", "1-5", "1,3,5-7". Omit for all pages. |
| path | string | yes | Absolute path to the source PDF. |
No output schema declared.
No examples provided.
What is the TruePath PDF MCP server?
TruePath PDF is an MCP server listed in the public MCP registry as io.github.JoyTruepath/truepath-pdf-mcp. Local-only PDF tools for AI, extract text, search, split/merge, render pages. Files never leave. This page covers its npm package (@truepathpdf/mcp-server).
Is the TruePath PDF MCP server safe to use?
TruePath PDF scores 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 24 September 2026. It declares no install or post-install scripts. 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 TruePath PDF MCP server expose?
TruePath PDF exposes 9 tools: get_info, extract_text, search, split, merge, and 4 more. Their descriptions and schemas cost roughly 1,218 tokens of context every time the server is loaded.
Is the TruePath PDF MCP server still maintained?
TruePath PDF is still listed as active in the MCP registry. We last reached this channel on 24 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 TruePath PDF MCP server under?
TruePath PDF declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.