tabnas
by tabnas.dev in Documents & files
Seven tools over the tabnas parsing engine: parse, validate, diagnose, fixtures, compare.
https://mcp.tabnas.dev/mcp
Last 30 days
- Uptime
- 100%
- Response time
- 300 ms typical, 300 ms slowest 5%
- Last check
- 5 h ago
- Next check
- in 45 min
How to call it
Add it to any MCP client that supports remote servers.
{
"mcpServers": {
"tabnas": {
"type": "http",
"url": "https://mcp.tabnas.dev/mcp"
}
}
}7 tools
- parse
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
- validate_grammar
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
- explain_parse_error
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
- test_grammar
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}
- list_plugins
List every bundled tabnas plugin descriptor (tabnas.plugin.json of each fleet repo), sorted by name. Returns {plugins:[...]}.
- describe_plugin
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.
- compare_grammars
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[],
Security scan
- No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.
Recent checks
| When | Result | HTTP | Time |
|---|---|---|---|
| 5 h ago | Passed | 200 | 300 ms |