Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Source-backed public tables with citations, claim checks, and reviewable corrections.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://skeletable.com/mcpRun this in your terminal
claude mcp add --transport http skeletable https://skeletable.com/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"skeletable": {
"url": "https://skeletable.com/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"skeletable": {
"type": "http",
"url": "https://skeletable.com/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
https://skeletable.com/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Tool names and descriptions exactly as the server reported them on Nov 6, 2026. The maker wrote them, not us; we show them as plain text.
list_tablesFind tables in the library. Each result gives its slug, the question it answers, its size and when it was last read.
get_tableRead a table: its scope, its columns with the rule for each, a summary of what each column holds, and its rows. A null value is blank. `origins` says where a row's unquoted values came from, `ai` says how far each AI column has got, and `versions` lists saved versions. For a big
get_cellThe evidence for one value: the source, the exact quote, what kind of source it is and when it was read. For a missing value, where we looked, and `absent` means the source was read and gives no such value. `url` is the cell's lasting address, showing its proof, for citing. `conf
check_claimTest a statement against one cell, such as whether a value in a draft or an answer is right. The verdict is `matches`, `differs` (with what the source states), `disputed` (sources disagree, see `conflicts`) or `unknown` (no acceptable source stated it, so say so). It compares val
export_tableA table as CSV, ready to save as a file or load into a notebook. The first column is each row's name unless `names` is false. `columns` picks columns by id, in that order. With `proof`, each column is followed by its source and quote, and in a table whose proof is optional, by wh
propose_changeSuggest a new value for a cell, with its proof. The quote must be word for word from the source and state the value. The owner reviews it before anything changes. Needs a token sent as a Bearer token.
create_tableMake a private draft table, ready to fill, for anything from a tracker to a dataset. Its values say where they came from unless you set `proof` to `required`. Only `title`, `columns` and `rows` are needed now, but give `question`, `scope`, and a `rule` for each column if you can:
add_columnsAdd columns to a draft you run, such as a blank one a person started. Returns the new column ids for fill_cells. Needs a token.
add_rowsAdd up to 500 rows to a table you run. Each row is a name, or an object with its `values` by column id or label, so a whole tracker or dataset goes in a few calls. A row without a `key` gets the next free number. A name the table already has gets the values given for it, so synci
fill_cellsSet up to 200 cells of a table you run. Usually a cell gives `value` and `origin` (`entered`, `imported` with a `note` like the file or email it came from, `link` with its `source`, or `generated`). Left out, the origin is `link` when there's a `source` and `generated` when there
data_linkA private address that loads a table you run as CSV, for a notebook, a script or a spreadsheet, with the lines to do it. Add `?columns=a,b` to pick columns and `?names=0` to leave out row names. Anyone with the link can read the data, and `fresh` makes a new one so the old one st
save_versionFreeze a table you run as it stands now, as a numbered version with a lasting link that never changes. Do this before training on a dataset or citing a table, and name the version you used. Needs a token.
fork_tableCopy a table into your own account as a private draft, to extend or relabel: any published public table, or one you run. Every value keeps its proof or origin, and the copy remembers where it came from. Needs a token.
set_instructionMake a column an AI column, change its instruction, or turn it back into a plain column with an empty one. The instruction says what to work out for each row and names other columns in braces, like "Classify {Pitch} by genre". Its values never overwrite what a person typed, linke
next_ai_cellsThe next prompts to answer for a table's AI columns, up to 200 at a time: blank cells first, then answers whose row or instruction has changed. Answer each prompt yourself, then send the answers back with fill_ai_cells, each with its `row` and `basis`. Repeat until it says `done`
fill_ai_cellsSave up to 200 answers to an AI column, each with the `row` and `basis` next_ai_cells gave it. An answer outside the column's choices, or to a prompt that has since changed, comes back with a reason. Each value is saved as generated, with the instruction and `model`. Needs a toke
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account eftpmc, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 260 ms (HTTP 200)
No sign-in needed
Read 16 tool descriptions and found no hidden instructions to the AI
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.0.0) reached the registry 5 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Spec Driven Development, Remote Desktop Commander, Python MCP
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Local-only Python MCP server for the Files.com API.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
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.
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 |
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:
Classify {Pitch} as Horror, Puzzle or Racing. The person's own agent answers it for each row through next_ai_cells and fill_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./owner/slug/v/2 and, for a public table, /data/owner/slug/v2.csv./d/ .csv load a private table into pandas or Google Sheets. ?columns=a,b picks columns and ?names=0 drops row names.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
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.
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.
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 | Check a table's shape, numbers and text against its quotes |
pnpm tables verify | Open each source and look for every quote |
pnpm tables watch | See whether live quotes are still on their pages, and save the result |
pnpm tables sample | 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.