Tablestakes
If you're wrangling GitBook or Notion exports where tables get collapsed into single-line HTML blobs, this converts them to clean pipe format for LLM reading and writes changes back without corrupting the markup. Exposes list_tables for discovery, read_table for extraction, and surgical operations like update_cells, insert_row, delete_column. All writes require a version hash to prevent stale overwrites. The token savings are real: 91% on table discovery, 39% on HTML reads, 73% on GFM edits compared to using generic file read/write tools. Handles both GitHub Flavored Markdown and GitBook's collapsed HTML with width attributes intact.
- GitHub stars
- 1
- tools
- 10
- transport
- STDIO
- last updated
- Mar 24, 2026
Tools
10 toolsPublic tool metadata for what this MCP can expose to an agent.
list_tablesScan file, return all tables with metadata + preview
Scan file, return all tables with metadata + preview
No parameter schema in public metadata yet.
read_tableFull table normalized to pipe format + version hash
Full table normalized to pipe format + version hash
No parameter schema in public metadata yet.
update_cellsBatch {row, column, value} patches
Batch {row, column, value} patches
No parameter schema in public metadata yet.
insert_rowInsert row at position (-1 to append)
Insert row at position (-1 to append)
No parameter schema in public metadata yet.
delete_rowRemove row by index
Remove row by index
No parameter schema in public metadata yet.
insert_columnInsert column with default value
Insert column with default value
No parameter schema in public metadata yet.
delete_columnRemove column
Remove column
No parameter schema in public metadata yet.
rename_columnRename header
Rename header
No parameter schema in public metadata yet.
replace_tableFull table replacement from pipe input
Full table replacement from pipe input
No parameter schema in public metadata yet.
create_tableCreate new table from pipe input (default: HTML)
Create new table from pipe input (default: HTML)
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
tablestakes
An MCP server that gives LLMs clean, surgical access to tables trapped in messy HTML.
The Problem
Tools like GitBook, Notion exports, and CMS platforms collapse tables into single-line HTML when syncing to Markdown files. The result looks like this in your editor:
<table><thead><tr><th width="520.11">Requirement</th><th width="122.07">Priority</th><th>Priority 1-2-3</th></tr></thead><tbody><tr><td><strong>1.1</strong> Agent sees only their Salesforce-assigned cases <strong>in the currently selected organization</strong> (case is "assigned" when SF <code>Case.OwnerId</code> matches the agent's linked SF user ID)...</td><td>Must</td><td>1</td></tr></tbody></table>
Details
- Repository
- github.com/oborchers/tablestakes
- Category
- Documents & Knowledge
- Package
tablestakes- Transport
- STDIO
- Registry
- MCP registry, active
Related Documents & Knowledge MCP servers
View all
TriliumNext (trilium-mcp)ovden13/trilium-mcpRead and write a self-hosted TriliumNext knowledge base over its ETAPI.1stars
FastMCP seed raise pipeline tracker — syncs from Obsidian CRM, generates meetingadelaidasofia/investor-relations-mcpFastMCP seed raise pipeline tracker — syncs from Obsidian CRM, generates meeting prep, tracks…0starsFastMCP server for bidirectional sync between personal and team Obsidian vaultsadelaidasofia/vault-sync-mcpFastMCP server for bidirectional sync between personal and team Obsidian vaults.0stars
Webscrape Mcpcarrasquelalex1/webscrape-mcpFetch any URL and get clean Markdown. Web scraping for AI agents.0stars
ClicheFactory Document Intelligenceclichefactory/clichefactory-mcpExtract structured JSON from PDFs, images, DOCX, XLSX, CSV, EML attachments, and DSPy pipelines.0stars
Iteration Layeriterationlayer/iterationlayerComposable APIs for document extraction, image transformation, and document & sheet generation.0stars