docsearch
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@docsearch search for 'Q4 targets' in the reports folder"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
docsearch
MCP server for searching and reading binary document files.
Requirements
uv (for
uvx)
Related MCP server: File Search Tool
Install
Claude Code
User-scope (available in all projects):
claude mcp add --scope user docsearch -- uvx --from git+https://github.com/AllenComm/mcp-docsearch docsearchProject-scope (available only in the current project):
claude mcp add docsearch -- uvx --from git+https://github.com/AllenComm/mcp-docsearch docsearchOr add directly to your MCP config (~/.claude/.mcp.json for user-scope, .mcp.json for project-scope):
{
"mcpServers": {
"docsearch": {
"command": "uvx",
"args": ["--from", "git+https://github.com/AllenComm/mcp-docsearch", "docsearch"]
}
}
}OpenCode
Add to your opencode.json:
{
"mcp": {
"docsearch": {
"type": "local",
"command": ["uvx", "--from", "git+https://github.com/AllenComm/mcp-docsearch", "docsearch"],
"enabled": true,
"timeout": 30000
}
}
}Agent Instructions
Add to your AGENTS.md or CLAUDE.md so your agent knows when to use these tools:
Use the docgrep and docread MCP tools instead of grep/read for binary documents (PDF, DOCX, PPTX, XLSX, ODT, ODS, ODP, RTF, EPUB).Supported Formats
Format | Extension | Extraction |
| Page-by-page text | |
Word |
| Paragraphs + tables |
PowerPoint |
| Slide-by-slide text frames + tables |
Excel |
| Sheet-by-sheet, tab-separated rows |
OpenDocument Text |
| Paragraphs |
OpenDocument Spreadsheet |
| Sheet-by-sheet, tab-separated rows |
OpenDocument Presentation |
| Slide-by-slide text |
Rich Text Format |
| Full text |
EPUB |
| Chapter-by-chapter text (spine order) |
Tools
docgrep
Search through documents for text matching a regex pattern. Returns filepath:section:matching_line.
Parameters:
directory(required) — path to search recursivelypattern(required) — regex pattern to matchcase_sensitive— defaultfalsefile_types— filter to specific extensions, e.g.["pdf", "docx"]max_results— default100
docgrep(directory="/home/user/reports", pattern="quarterly revenue")
docgrep(directory="/home/user/docs", pattern="TODO|FIXME", file_types=["docx"])docread
Read full text content from a single document. Output is auto-truncated at 40,000 characters — use range to narrow results for large documents.
Parameters:
filepath(required) — path to the documentrange— filter to specific sections by format:PDF: page numbers, e.g.
"1-5","3","1,3,5-7"PPTX/ODP: slide numbers, e.g.
"2-3"XLSX/ODS: sheet name or 1-based index, with optional row range after colon, e.g.
"1","Sheet1","1:1-100","Revenue:50-200"EPUB: chapter numbers, e.g.
"1-5"DOCX/ODT/RTF: line numbers, e.g.
"1-50","100-200"
docread(filepath="/home/user/reports/q4.pdf", range="1-3")
docread(filepath="/home/user/data/sales.xlsx", range="1:1-100")
docread(filepath="/home/user/data/sales.xlsx", range="Revenue:50-200")Available Tools
2 toolsdocgrepA
Search through document files (PDF, DOCX, PPTX, XLSX, ODT, ODS, ODP, RTF, EPUB) for text matching a regex pattern. Returns grep-like output: filepath:section:matching_line
Inputs: pattern (required), directory (required), file_types, max_results, +1 more. Returns: result
docreadA
Read and extract text from a document file (PDF, DOCX, PPTX, XLSX, ODT, ODS, ODP, RTF, EPUB). Returns sections formatted as '=== section_label ===\ntext'. Output auto-truncated at 40000 chars.
Inputs: filepath (required), range. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: docgrep searches for regex patterns across documents, while docread extracts full text. No overlap in functionality.
Both tools follow a consistent 'doc' prefix + action verb pattern (docgrep, docread), making their purpose immediately clear.
With only two tools, the server is minimal but covers the core actions of searching and reading documents. While a bit sparse, it's reasonable for a focused utility like document search.
The server lacks essential operations for managing the document collection, such as listing, adding, or deleting documents. Users cannot upload or remove documents, limiting the toolset to read-only access.
Maintenance
Related MCP Connectors
Document-to-Markdown MCP server — convert PDF, Office and HTML into LLM-ready Markdown.
Document conversion MCP server: PDF to Markdown, image OCR, spreadsheet parsing.
MCP server for detecting and redacting PII (Personally Identifiable Information) in PDF documents.
Document processing over MCP: merge, split and compress PDFs, run OCR, extract document text.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceUniversal MCP server for extracting text from various document formats including PDF, Excel, Word, CSV, and more, with support for streaming, limits, and markdown conversion.3MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that enables file system search and inspection, including directory listing, regex-based file name and content searches, and reading text, PDF, and DOCX files.1MIT
- FlicenseNot gradedqualityBmaintenanceA local MCP server providing read-only access to documents like Word, PDF, Excel, and images, with file listing, reading, and metadata extraction.1-
- AlicenseNot gradedqualityDmaintenanceMCP server that extracts clean text, tables, and structured data from documents, images, code, and audio files, supporting 97 formats with OCR, transcription, and code intelligence.MIT