Skeletable MCP server
Commit Nov 2, 2026Allows AI agents to read, build, and propose changes to source-backed tables with verifiable citations and claim checks.
Also known as eftpmc/skeletable
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.0.0
- Last commit
- Nov 2, 2026
- License
- Apache-2.0
What is Skeletable MCP?
Skeletable allows AI agents to read, build, and propose changes to source-backed tables with verifiable citations and claim checks.
Summary generated from the project's README
About Skeletable MCP server
Skeletable provides a way for AI agents to interact with source-backed tables that prioritize verifiable data. It allows agents to read, build, and propose changes to datasets where every value is linked to a specific origin, such as a file, a person, or a model. This system is designed for developers and users who need to maintain trackers or datasets with high integrity through claim checks and citations.
The server operates over HTTP at a specific endpoint and can be added to clients like Claude using the transport flag. While reading tables requires no account, performing write operations like building drafts or proposing changes requires a Bearer token from the user settings. Agents work within a draft system where they can add up to 500 rows at a time or manage AI columns that use specific instructions to classify or process data.
Users can manage data through tools like list_tables, get_table, and propose_change. The platform supports versioning to freeze tables with permanent links and offers data links for loading private CSVs into notebooks or spreadsheets. It distinguishes itself by ensuring that every value includes a source, an exact quote, or a record of where the system looked for information.
What you can do with it
- 1Verify data accuracyAn agent can test a specific statement against a table cell to see if it matches or is disputed.
- 2Automate data classificationA developer can set up AI columns with instructions to automatically categorize rows in a dataset.
- 3Propose verifiable updatesAn AI agent can suggest new values for a table by providing the necessary proof and citations for a human to review.
- 4Export structured datasetsUsers can download tables as CSV files including the original quotes and sources for every value.
Written from the project's README. Every use case is checked against a quote from it.
How to install Skeletable MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Skeletable MCP in Claude Code
$ claude mcp add --transport http skeletable https://skeletable.com/mcpInstall Skeletable MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"skeletable": {
"url": "https://skeletable.com/mcp"
}
}
}Install Skeletable MCP in VS Code
.vscode/mcp.json
{
"servers": {
"skeletable": {
"type": "http",
"url": "https://skeletable.com/mcp"
}
}
}Install Skeletable MCP in VS Code CLI
$ code --add-mcp '{"name":"skeletable","type":"http","url":"https://skeletable.com/mcp"}'Install Skeletable MCP in Codex
$ codex mcp add skeletable --url https://skeletable.com/mcpInstall Skeletable MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.skeletable] url = "https://skeletable.com/mcp"
Install Skeletable MCP in Gemini CLI
$ gemini mcp add -s user --transport http skeletable https://skeletable.com/mcpInstall Skeletable MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"skeletable": {
"url": "https://skeletable.com/mcp",
"type": "http"
}
}
}Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableeftpmc/skeletable is public and reachablegithub.com/eftpmc/skeletable ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-02github.com/eftpmc/skeletable ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-06-18 in 140 msPass
README
View on GitHubSkeletable
Tables for people and agents, where every value records where it came from: a linked page, a person, a file or another app, or a model. Use one for a tracker, a dataset or a list. A new table works this way by default. A table can also require proof, as every table in the public library does: then each value links to the source and exact words that state it, or says where we looked. People read tables on the site, and agents read and build them through an MCP server.
Connect
The server takes MCP over HTTP at /mcp. Reading needs no account. Proposing a change or building a draft needs a token from Settings, sent as a Bearer token. An agent can only write to drafts its person runs, each value still passes every check, and a person publishes.
claude mcp add --transport http skeletable https://skeletable.com/mcp
| Tool | What it does |
|---|---|
list_tables |
Find a table by what it covers |
get_table |
Read a table: its scope, columns, a summary of each column, and its rows, live or as a saved version |
get_cell |
One value's source, exact quote and date, or where we looked |
check_claim |
Test a statement against a cell: it matches, differs, is disputed, or is unknown |
export_table |
A table as CSV, live or a saved version, with chosen columns, and optionally each value's source, quote and origin |
propose_change |
Suggest a new value with its proof, for the owner to review |
create_table |
Make a private draft, ready to fill. proof: "optional" makes one for working data |
add_columns |
Add columns to a draft, including AI columns with an instruction |
add_rows |
Add up to 500 rows a call, each by name or with its values. A row it already has gets the new values |
fill_cells |
Fill a draft's cells with proof, or say where you looked. Where proof is optional, a value can give its origin instead. Replies list only what failed |
data_link |
A private CSV address for a notebook, script or spreadsheet, with the lines to load it |
save_version |
Freeze a table as a numbered version with a link that never changes |
fork_table |
Copy a public table, or one you run, into your account as a private draft |
set_instruction |
Make a column an AI column, change its instruction, or clear it |
next_ai_cells |
The next prompts for a table's AI columns, each with a fingerprint |
fill_ai_cells |
Save the agent's answers to an AI column |
Datasets
A table whose proof is optional is a dataset. Its values say where they came from: a linked page, a person, a file, or a model. On top of that:
- AI columns have an instruction, like
Classify {Pitch} as Horror, Puzzle or Racing. The person's own agent answers it for each row throughnext_ai_cellsandfill_ai_cells, so Skeletable never runs a model itself. Each answer records the model and a fingerprint of its prompt, so a changed row shows its answer is out of date. A value a person typed is never overwritten. - Versions freeze a table with a lasting link, at
/owner/slug/v/2and, for a public table,/data/owner/slug/v2.csv. - Column summaries show what each column holds: categories with counts, text lengths, number ranges, and where values came from.
- Data links at
/d/<key>.csvload a private table into pandas or Google Sheets.?columns=a,bpicks columns and?names=0drops row names. - Forks copy a public table into your account to extend or relabel, and remember where they came from.
What's here
tables/ The tables, how they're scored, and their check results
packages/tables The table format and its checks
apps/mcp The server: the MCP endpoint and the JSON the site reads
apps/web The site, built with shadcn/ui and served by the server
docker/ The server's image, which Railway builds
Licensing
The source code is licensed under Apache-2.0. Published table data is licensed separately under CC BY 4.0, as shown in the data responses.
Review table changes
Each table has Overview, Proposals, and History tabs, with an Open sheet button for the editor. Signed-in contributors can create a titled proposal with up to 20 cell changes, a reason, and a source and exact quote for each value. Bundles remain open for review, including when submitted by an owner. Existing single-cell owner saves still apply immediately after validation.
Account owners and editors can accept all changes in a bundle or close it. Acceptance is transactional and refuses a bundle if any cell has a newer version than the one recorded at submission. Close a stale proposal and submit an updated one. Accepted values remain in the existing version history. Discussion threads, revision restore, and editing an open proposal are not implemented yet.
Develop
Requirements: Node 22+ and pnpm 10 (corepack enable).
pnpm install
pnpm dev
| Command | What it does |
|---|---|
pnpm dev |
Run the server on port 4200 |
pnpm dev:web |
Run the site on port 5173, reading from that server |
pnpm test |
Run tests |
pnpm lint |
Lint |
pnpm typecheck |
Type-check every package |
pnpm build |
Production build |
pnpm tables validate <file> |
Check a table's shape, numbers and text against its quotes |
pnpm tables verify <file> |
Open each source and look for every quote |
pnpm tables watch <file> |
See whether live quotes are still on their pages, and save the result |
pnpm tables sample <file> |
Draw a repeatable sample of cells for spot-checking |
New tables start as JSON files in tables/, and the server loads them into Postgres when DATABASE_URL is set, or serves them directly when it isn't. It refuses to start if a table fails its checks.
Sign-in needs DATABASE_URL, GOOGLE_CLIENT_ID and GOOGLE_CLIENT_SECRET. PUBLIC_URL sets the site's address, and OWNER_EMAIL says who runs the official account.
Database tests run when TEST_DATABASE_URL is set. They wipe that database.
Skeletable MCP questions
How do I add Skeletable MCP to Claude Code?
Run claude mcp add --transport http skeletable https://skeletable.com/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Skeletable MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Does reading tables require an account?
No, reading tables does not require an account, but proposing changes or building drafts requires a Bearer token from Settings.
Can I use Skeletable to create datasets?
Yes, a table where proof is optional is considered a dataset, allowing values to record origins from pages, people, files, or models.
How does the AI column functionality work?
AI columns use instructions to classify or process data; the agent provides answers through specific tools, and Skeletable records the model and prompt fingerprint used.