Atlas / MCP servers / intsig-textin / Textin

TextinSAFE

mcp/intsig-textin/textin
Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
4 4r · 0w · 0d
Transport
stdio
License
MIT
Stars
29
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

English | 中文

TextIn OCR MCP Server

TextIn MCP Server is a tool for extracting text and performing OCR on documents, including document text recognition, ID recognition, and invoice recognition. It also supports converting documents into Markdown format.

Tools

  • recognition_text
  • Text recognition from images, Word documents, and PDF files.
  • Inputs:
  • path (string, required): file path or a URL (HTTP/HTTPS) pointing to a document
  • Return: Text of the document.
  • Supports conversion for:
  • PDF
  • Image (Jpeg, Jpg, Png, Bmp)
  • doc_to_markdown
  • Convert images, PDFs, and Word documents to Markdown.
  • Inputs:
  • path (string, required): file path or a URL (HTTP/HTTPS) pointing to a document
  • Return: Markdown of the document.
  • Supports conversion for:
  • PDF
  • Microsoft Office Documents (Word, Excel)
  • Image (Jpeg, Jpg, Png, Bmp)
  • general_information_extration
  • Automatically identify and extract information from documents, or identify and extract user-specified information.
  • Inputs:
  • path (string, required): file path or a URL (HTTP/HTTPS) pointing to a document
  • key (string[], optional): The non-tabular text information that the user wants to identify, input format is an array of strings.
  • table_header (string[], optional): The table information that the user wants to identify, input format is an array of strings.
  • Return: The key information JSON.
  • Supports conversion for:
  • PDF
  • Microsoft Office Documents (Word, Excel)
  • Image (Jpeg, Jpg, Png, Bmp)

W

Read from source at commit c3357662ccc4OBSERVED · 2026-10-08
Advertisement
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code
claude mcp add server-textin --env APP_SECRET=${APP_SECRET} -- npx -y @intsig/[email protected]
claude-desktop
{
  "mcpServers": {
    "server-textin": {
      "command": "npx",
      "args": [
        "-y",
        "@intsig/[email protected]"
      ],
      "env": {
        "APP_SECRET": "${APP_SECRET}"
      }
    }
  }
}
03

Exposed tools (4)

4 read · 0 write · 0 destructive.

ToolRiskDescription
doc_to_markdownreadConvert images, PDFs, and Word documents to Markdown.
general_information_extrationreadAutomatically identify and extract information from documents, or identify and extract user-specified information.
read_filereadRead the complete contents of a file from the file system.
recognition_textreadText recognition from images, Word documents, and PDF files.
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
declared (2 observation(s))
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (1)

LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
axios, zod-to-json-schema, @types/node, typescript
Why it matters. 4 dependency range(s) float
Fix. pin exact versions or ship a lockfile

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha c3357662ccc4full audit observations/trust-audit/mcp-server/intsig-textin__textin.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-08c3357662ccc4SAFEB89first audit
06

Questions

What tools does Textin expose?

4 in total: 4 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Textin safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does Textin need?

It reads APP_SECRET from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does Textin run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as @intsig/server-textin at 0.1.7.

How current is this page?

The grade is for one exact copy of the source (c3357662ccc4), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement