officegrep

officegrep

[ci] [license: MIT] [python] [MCP]

Full-text search inside Word, PowerPoint, Excel and PDF — for agents.

grep cannot see a single character inside a .docx. officegrep extracts the text, indexes it into one SQLite file, and hands it to any agent over MCP.

$ officegrep search "bending moment"
Found 3 hits:
F:\reports\pole-design.docx  [table p 89]  design bending moment (load point 0.25 m from tip); deflection limit; test moment = 2× …
F:\notes\composites.md  [line 32]  … utilization 81%. **test bending moment = 2× the standard test moment** …

中文说明：README.zh-CN.md

Why

• grep / ripgrep only read plain text. .docx is a zip of XML, .xlsx keeps strings in a shared table, .pdf is a compressed stream.
• Generic RAG needs an embedding service, a vector store, and a network round-trip.
• This needs one SQLite file: offline, incremental, milliseconds.

Install

# one command, no clone, no uvpip install https://github.com/Asgoresmilelong/officegrep/releases/download/v0.1.1/officegrep-0.1.1-py3-none-any.whl
# or from sourcepip install git+https://github.com/Asgoresmilelong/officegrep

Runtime deps: lxml, openpyxl; PDF support adds optional pypdf.

Listed in the official MCP Registry as io.github.Asgoresmilelong/officegrep; there is also an .mcpb bundle on the releases page for MCP hosts that install bundles (needs uv).

CLI

officegrep index ~/Documents ~/Downloads     # build / update (incremental)officegrep search "island reef" --limit 5officegrep search "wind load" --under ~/Documentsofficegrep stats

The index lives in ~/.officegrep/index.db; override with --db or OFFICEGREP_DB.

First run

Nothing to do. If the index is empty when officegrep mcp starts, it scans ~/Documents, ~/Downloads and ~/Desktop in the background (25 MB per-file cap) while the agent keeps talking; a search_docs call made in the meantime answers with a "still building" note instead of a misleading "no results".

• opt out: OFFICEGREP_AUTOINDEX=0
• scan other folders: OFFICEGREP_ROOTS="~/work;~/papers"

Stay in sync

officegrep watch ~/Documents           # re-index on change: 2s poll, no extra dependencyofficegrep watch ~/Documents --once    # single sync pass (cron / CI friendly)

Or let the MCP server watch in the background:

OFFICEGREP_WATCH="~/Documents;~/Downloads" officegrep mcp

The index runs in WAL mode, so a watch process and an MCP server can share one database file concurrently — something that fails with database is locked on a default rollback journal.

MCP server

officegrep mcp

Client config (Claude Desktop / Cursor / Codex / any MCP host):

{  "mcpServers": {    "officegrep": {      "command": "officegrep",      "args": ["mcp", "--db", "/Users/me/.officegrep/index.db"]    }  }}

The protocol is a hand-written JSON-RPC over stdio — no MCP SDK dependency.

How it works

docx / pptx  →  zipfile + lxml, read the XML directlyxlsx         →  openpyxl (read_only)pdf          →  pypdf (optional)txt / md     →  line chunks, line numbers kept

• Every block carries a human-readable locator, because the first question an agent asks is "where?".
• The index uses SQLite FTS5 with the trigram tokenizer: substring matching for both CJK and Latin text, no word segmenter required, ranked by bm25().
• Queries of 1–2 characters cannot match trigrams, so they fall back to a scan ranked by hit count (CJK queries are frequently two characters).
• Incremental: compare (size, mtime) first, hash with SHA-1 only when they differ.

Benchmark on a real engineering corpus:

Limits

• No OCR: scanned PDFs yield nothing.
• Literal search, not semantic — "tower" will not find "pole" unless both appear.
• 1–2 character queries scan the table; slow past a few hundred thousand blocks.
• Indexes body text only: no comments, tracked changes, headers or footers.

License

MIT