MCP.Market

tabnas MCP server

online · 100% uptime
by tabnas.dev·dev.tabnas/mcp·v0.1.20
No reviews yet

Seven tools over the tabnas parsing engine: parse, validate, diagnose, fixtures, compare.

A88/100grade A
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
A88/100

full report

Adoption
Growing

0 stars117 downloads/wk

Reviews

Write one

Nobody has reviewed tabnas yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

tabnas tools (7, 1 write)

write = sends, deletes, buys or posts
  • compare_grammarsFree

    Grammar compatibility (AX plan Phase 5): does candidate grammar B still accept what baseline A accepted, and does it build the same tree for inputs both accept? Returns EVIDENCE AND CONFIDENCE, never a bare verdict: {normalForm, proven[], observed[], changes[], counterexamples[], confidence, why}. confidence:'low' with a stated reason is a successful run, not a failure — language inclusion is undecidable in general, so anything outside the decidable subset is reported not-proven rather than incompatible. Supply `corpus` (real inputs) for the tier that measures what your documents actually do.

  • describe_pluginFree

    The full descriptor for one plugin, by package name ('@tabnas/csv') or bare fleet name ('csv'). Unknown names get {ok:false, errors} naming the known plugins.

  • explain_parse_errorFree

    Parse input and explain the failure. Returns {failed:false} when the input parses; otherwise {failed:true, diagnostic, registry} where registry is the error-code registry entry {code,message,hint} for the diagnostic code (resource tabnas://errors), or null for a code the bundled registry does not know (e.g. a plugin-declared code).

  • list_pluginsFree

    List every bundled tabnas plugin descriptor (tabnas.plugin.json of each fleet repo), sorted by name. Returns {plugins:[...]}.

  • parseFree

    Parse input with the tabnas engine. Returns {ok:true, tree} or, on parse failure, {ok:false, diagnostic} — the structured diagnostic described by resource tabnas://schema/diagnostic. An invalid grammar is rejected as {ok:false, errors:[{path,message}]}. Without a grammar the bare engine is used, which defines no rules and produces an undefined tree for every input.

  • test_grammarwrite actionFree

    Run TSV fixture content against a grammar in a fresh instance, using the fleet fixture convention (@tabnas/support): line 1 is a header, the input column is escape-decoded, the expected column is JSON or ERROR / ERROR:<code>. Returns {pass, fail, rows:[{row,input,expected,got,ok}]}. Refuses more than 10000 rows.

  • validate_grammarFree

    Validate a serialized GrammarSpec. Structural validation against the bundled grammar schema, an engine load in a fresh instance, and a check that every rule reference (`p`, `r`) names a rule the grammar actually defines — a dangling reference loads cleanly and then fails at parse time with `unknown_rule`. Returns {ok:true, v} (v = declared builtin config-schema version, absent means 1) or {ok:false, errors:[{path,message}]}. Security: a grammar carrying a `ref` key, or any function reference that is not a $-suffixed engine builtin, is rejected — validating a grammar never runs supplied code.

Public scan report

scanner v0.1.10 · 2026-11-01 · same rubric, same numbers if you re-run it

1 high
  • Code scan32 source files scanned25/25
  • Live reliabilityremote reachable in 283ms20/20
  • Tool poisoning7 tool descriptions checked15/15
  • Auth qualityopen endpoint exposes 1 write-action tools with no auth3/15
  • Maintenancelast push 24 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year; website matches verified namespace10/10

Findings (1)

  • highWrite-action tools reachable without authenticationauth.open-write
Overall 88/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How tabnas compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
88/100
higher than 75% of 48,255 servers
Tools
7
the typical server has 7
Tools that change things
14%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote server answers 100%
Response time
138 ms
faster than 75% of 30,031 servers
Downloads a week
117
more than 66% of 12,191 servers with a package

What its tools let an agent do: 6 read · 1 change

Release history: 4 versions in the registry since 2026-08-22, latest 2026-10-08, typically one every 10 days.

Install tabnas in Claude Code, Cursor or VS Code

claude mcp add --transport http mcp https://mcp.tabnas.dev/mcp
Add to Cursor

What the publisher says

From the tabnas repository's README, as published. We do not edit it. Read it on GitHub

tabnas/mcp

The tabnas agent tooling: one TypeScript codebase, two front-ends: an MCP server (stdio) and the unified tabnas CLI, sharing a single core (ts/src/core.ts) so the two can never disagree. For each operation the CLI's --json output and the MCP tool result are byte-identical, and the test suite holds them to it.

The website page for this package: per-client setup, the tool contracts, the hosted endpoint's bounds: tabnas.dev/mcp.

Published as @tabnas/mcp. This repo is TypeScript-only: it is tooling over the engine, not a parity package, so there is no Go port.

Install

npm install -g @tabnas/mcp     # the `tabnas` CLI
npx --yes @tabnas/mcp          # run the MCP server directly (stdio)

MCP client configuration (stdio):

{
  "mcpServers": {
    "tabnas": {
      "command": "npx",
      "args": ["--yes", "@tabnas/mcp@<x.y.z>", "mcp"]
    }
  }
}

Fill in with the current version: npm view @tabnas/mcp version. This README does not name it: a repo cannot carry an exact pin of its own published version, because the commit that updates it becomes the next release's content, leaving it one release behind forever.

The server is started by the mcp subcommand of the CLI (tabnas mcp), which is exactly what the skills package's mcp.json invokes as npx --yes @tabnas/mcp@ mcp. (--yes matters: on a cache miss npx would otherwise prompt on the stdin the MCP transport owns. Pin an exact version so the tools cannot drift under an installed client: skills/mcp.json carries the real one, written from the registry by its tools/sync-mcp-pin.js and checked by tools/validate.js --online.)

The seven tools

Notes on the contracts:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

tabnas: common questions

Is tabnas MCP server safe?
Yes, by our scan: it is graded A (88/100). Read the tabnas safety report
How do I install tabnas?
It runs remotely at mcp.tabnas.dev. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does tabnas need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is tabnas maintained?
The last commit was 27 days ago (2026-10-08). The latest release is v0.1.20.
Is tabnas up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
How does tabnas compare with other MCP servers?
safety score 88/100 (higher than 75% of 48,255 servers); tools 7 (the typical server has 7); tools that change things 14% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.