Match – A pattern matching language that replaces regex
Regex alternative with parse trees and zero backtracking; niche but genuinely better.
Surgical Google Docs editing for AI agents — search/replace, insert, comments, and more. MCP server.
Search/replace editing beats character indices that break every other Google Docs MCP.
Developers building AI agents that interact with Google Docs
Cursor · Continue · Sourcegraph Cody
All the Google Docs MCPs out there seem to be broken in annoying ways so I thought I'd make one. For instance they do character-offset-based editing and LLMs are reliably terrible at counting characters.
This one just works. (It uses the similar pattern-matching search and replace that code editor harnesses use for file editing to minimize token usage and latency).
There are some showstoppers still. The most annoying is that Google Docs comments API is has been broken for over a decade (sic). I (well, Claude) build a workaround that involves inserting a bookmark with the Apps Script API and linking to that bookmark from the comment. It's hacky but for a lot of LLM-based workflows like contract review or similar it gets you 80% of where you want to be - you can say something like "add comments and [email protected] for anything that you want their opinion on".
I hope people find it useful. Install involves the usual dance with Google Cloud API console; apologies in advance for taking some happiness from your day.
Regex alternative with parse trees and zero backtracking; niche but genuinely better.
AI edits as Google Docs suggestions, not silent replacements like Grammarly.
Structured pattern library beats noisy memory for LLM agents.
558x faster pattern matching in the kernel using Aho–Corasick, handles fragmentation correctly.
Token-efficient Google Docs editing for AI agents when gws and gogcli struggle with meaningful changes.
Vague research protocol with no demo, methodology link, or verifiable outcomes.