OR Key
drop another .md file to compare - side-by-side diff against xano-mcp

xano-mcp

Checks that your data connections are healthy and responding.
description: "Triggers on prompt mention of 'xano-mcp'."
personal 2 files 10 recent evals
Export

What it does for you

Checks that your data connections are healthy and responding.

What it produces

A recent result, so you can see the kind of work it returns.

loading…

How to get it

These run inside the Snappy workspace. Want this working in your business? I set skills like this up with you, in one focused week.

Work with me
For developers how this skill is built, graded, and how it runs

at a glance- the short version

actorExported functions in state/lib/xano-mcp.ts.
auditorNone wired yet - eval is manual (Robert review).
eval modeshape
categoryIntegrations
stages1

what's inside - the parts that make up a skill 3/4 present

A skill is just a few plain-text files. Only the main one is required. The rest are optional, added as the work needs them. This is what the skill is made of; how it runs is just below.

The skill
state/skills/xano-mcp/SKILL.md present
the skill itself, in plain text
The main file. It says what the skill is and lays out the steps in plain English.
Code
state/lib/xano-mcp.ts present
code the skill can run
Reusable code this skill can call when it needs to.
Scripts
state/bin/xano-mcp/ not present
helper scripts
Optional. Added when a skill has a few commands to run.
Loader
state/skills/xano-mcp/AGENTS.md present
what the AI loads on the fly
Loaded automatically the moment this skill is needed. Kept short on purpose.

how it's graded - what counts as a good run 3 criteria · 3 deterministic

Each row is one thing a good run has to get right. deterministic means a quick check decides, pass or fail. judge means the AI reads the result and rates it. Grading each piece on its own (instead of one overall score) shows exactly where a run fell short, so the fix is obvious.

name
kind
check
check_health_invocation
deterministic
The 'checkHealth' function in 'state/lib/xano-mcp.ts' is called successfully with 'checkHealth_input'.
test_endpoint_invocation
deterministic
The 'testEndpoint' function in 'state/lib/xano-mcp.ts' is called successfully with 'testEndpoint_input'.
pending_eval_logged
deterministic
A row is appended to 'state/log/pending-eval.ndjson' for each run as described in the 'Eval' section.

how it runs - the shared frame every skill uses 5/5 present

Every skill runs the same way. One part does the work, a separate part checks it, and a short loader hands the AI exactly what it needs for the job. Anything this skill doesn't use shows a one-line note saying why, on purpose, not by accident.

makes the work The worker
present
Exported functions in state/lib/xano-mcp.ts. the worker
Does the actual work. Whatever it produces is what gets checked next.
checks the work The reviewer
present
None wired yet - eval is manual (Robert review). the checker
A separate checker grades the work, so the part that made it can't approve its own work.
frame
learns Self-correction
present
fixes itself learns from gaps
When a run hits a gap, the skill gets edited on the spot [FIXED] or queued for a bigger rewrite [LOGGED], so it keeps getting better.
tidies up Background fixes
present
queued for rewrite runs in the background
Bigger fixes that can't be made on the spot get queued and rewritten in the background later.
remembers Run history
present
state/log/pending-eval.ndjson pending runs
Every run is written down here, then reviewed by hand each week.
Critical rules the things this skill must not get wrong
  1. snappy-os has a NO-MCP rule (program.md "Don't list") — this skill is health-checking an EXTERNAL MCP server (Xano's), NOT a license to add MCP into snappy-os internals
  2. READ-ONLY — checkHealth() and testEndpoint() do not mutate; never extend this skill into a deploy/mutate path
  3. ALWAYS use the typed lib state/lib/xano-mcp.ts rather than poking the MCP HTTP surface ad-hoc
  4. Eval is manual (Robert review) — every run files to state/log/pending-eval.ndjson

what it has learned - fixes written back in over time sample

When a run hits something this skill didn't handle, the fix gets written back into the skill so it doesn't happen again. FIXED means it was corrected on the spot. LOGGED means it's queued for a bigger rewrite. Either way, the skill gets a little better and never makes the same mistake twice.

  1. Loading feedback rows…

how the work flows- who makes it, who checks it

actor Exported functions in state/lib/xano-mcp.ts.
auditor None wired yet - eval is manual (Robert review).
1 data
eval log
`state/log/pending-eval.ndjson` (manual)
+ eval for this step

SKILL.md- the skill, written out in plain English

xano-mcp

MCP server health checks and tool testing.

Ported from kernel snappy-xano-mcp in Phase 0.5. See state/lib/xano-mcp.ts for the full API surface.

Steps

  • checkHealth() - see state/lib/xano-mcp.ts
  • testEndpoint() - see state/lib/xano-mcp.ts

Eval

Actor: the exported functions in state/lib/xano-mcp.ts. Auditor: none wired yet - eval is manual (Robert review). File a state/log/pending-eval.ndjson row on each run.

Score convention:

OutcomeScore
Pass on first try1.0
Failed first, auto-fix applied, re-check passed0.5
Still failing or unrecoverable0.0

Gotchas

via the Phase 0.5 driver. Only these rewrites were applied: already in state/lib/)

  1. realpathSync(process.argv[1]) CLI guard wrapped in try/catch
  • See the kernel SKILL.md for the original long-form guidance if you need it

(read-only reference at the kernel path above).

Graduation

This skill is prose. Graduate by defining a deterministic auditor and flipping eval: auto.

Rubric

criteria:
  - name: check_health_invocation
    kind: deterministic
    check: "The 'checkHealth' function in 'state/lib/xano-mcp.ts' is called successfully with 'checkHealth_input'."
  - name: test_endpoint_invocation
    kind: deterministic
    check: "The 'testEndpoint' function in 'state/lib/xano-mcp.ts' is called successfully with 'testEndpoint_input'."
  - name: pending_eval_logged
    kind: deterministic
    check: "A row is appended to 'state/log/pending-eval.ndjson' for each run as described in the 'Eval' section."

AGENTS.md- what the AI loads when this skill comes up

xano-mcp - loader

Per-turn rules for the xano-mcp skill. Full reference: state/skills/xano-mcp/SKILL.md. Do not skip these.

Critical Rules

  • snappy-os has a NO-MCP rule (program.md "Don't list") - this skill is health-checking an EXTERNAL MCP server (Xano's), NOT a license to add MCP into snappy-os internals
  • READ-ONLY - checkHealth() and testEndpoint() do not mutate; never extend this skill into a deploy/mutate path
  • ALWAYS use the typed lib state/lib/xano-mcp.ts rather than poking the MCP HTTP surface ad-hoc
  • Eval is manual (Robert review) - every run files to state/log/pending-eval.ndjson

Commands

| ui dashboard | state/skills/xano-mcp/resources/ui.openui | |library: state/lib/xano-mcp.ts - checkHealth(), testEndpoint() |eval log: state/log/pending-eval.ndjson (manual)

OpenUI Resource

  • Skill-owned OpenUI Lang resource: state/skills/xano-mcp/resources/ui.openui. Read it before rendering or editing this skill's generated component surface.
  • Treat this resource as a first-class artifact of the skill, not a generic chat response. Improve it when the skill's user-facing output needs to become richer.
  • System resources compose OpenUI primitives and inherit SnappyChat tokens. Use ui_contract: branded in SKILL.md only for deliberate platform or client visuals.

Known Pitfalls

  • Confusing "this skill talks to an MCP server" with "snappy-os may use MCP" - the rule is internal: snappy-os own code uses HTTP/CLI/local files only

Self-Test

An agent reading this should correctly:

  1. [ ] Treat this skill as read-only health-checking of an external server?
  2. [ ] Refuse to introduce MCP as a transport inside snappy-os just because this skill exists?
  3. [ ] File a pending-eval.ndjson row since the auditor is still manual?

Self-report

If this loader fell short, append a line:

echo "[$(date -u +%FT%TZ)] xano-mcp: <what was missing>" >> state/log/loader-feedback.log

<!-- kernel-ok: historical attribution for the PID-loader pattern. -->

Self-correcting loader (PID feedback)

This is the rule that makes loaders learn. Ported from snappy-kernel, where it demonstrably worked: the snappy-dom-cartographer skill mapped Skool admin UI once, every later ship-agent inherited the full map for free.

Before you finish, do two things:

1. Fix gaps (P - proportional). MANDATORY. If this loader didn't cover your case - if you had to read another file, run an undocumented command, work around a wrong selector, or discover a quirk - you MUST attempt an Edit to this AGENTS.md before you log.

  • Default action: edit this file. Surgical. Add the missing line, table

row, or code example where it belongs. No restructuring.

  • Only LOGGED is allowed when: the fix needs >10 lines, spans multiple

files, or requires a structural rewrite. In that case the state/regen/drain.sh queue picks it up asynchronously.

  • "I didn't have time" / "it's minor" / "the next agent will figure it out"

are NOT valid reasons. Minor gaps compound - that's the whole point of this loop.

  • Concrete example of a valid P-fix: discover agent-browser screenshot

takes path positionally not as --output <path>. One line in a table. Edit it in. Do not just log it.

  • The goal: the next agent never has to leave the loader.

2. Log the result.

echo "[$(date -u +%FT%TZ)] xano-mcp: <what was missing or fixed> [FIXED|LOGGED]" >> state/log/loader-feedback.log
  • FIXED = you patched this loader inline (P-fix).
  • LOGGED = too large for inline; the PostToolUse enqueue + Stop-hook drain

will rewrite the loader from scratch on next session-end.

Do not skip this. Every agent run must leave the system better than it found it. The loader is the setpoint; you are the sensor; the gap is the error signal; closing the gap is the correction.

api.ts- the code it can call

#!/usr/bin/env npx tsx
/**
 * snappy-xano-mcp/api.ts -- MCP server health checks and tool testing.
 *
 * Hits the deployed Cloudflare Worker at xano.snappy.ai.
 * Uses XANO_METADATA_TOKEN for authenticated Xano endpoint tests.
 *
 * Usage:
 *   npx tsx api.ts health          # check MCP server health
 *   npx tsx api.ts test <tool>     # test a specific MCP tool via Xano
 *
 * Or import as module:
 *   import { checkHealth, testEndpoint } from "./xano-mcp.ts";
 */

import { env } from "./env.ts";
import { realpathSync } from "fs";

const MCP_URL = "https://xano.snappy.ai";
const XANO_BASE = "https://xnwv-v1z6-dvnr.n7c.xano.io";

// --- Public API ---

export async function checkHealth(): Promise<{
  healthy: boolean;
  status: number;
  sseReachable: boolean;
  message: string;
}> {
  try {
    const res = await fetch(`${MCP_URL}/sse`, {
      method: "GET",
      headers: { Accept: "text/event-stream" },
      signal: AbortSignal.timeout(10000),
    });
    return {
      healthy: res.status === 200,
      status: res.status,
      sseReachable: true,
      message: res.status === 200 ? "MCP server reachable, SSE endpoint responding." : `Unexpected status: ${res.status}`,
    };
  } catch (err: any) {
    return {
      healthy: false,
      status: 0,
      sseReachable: false,
      message: `MCP server unreachable: ${err.message}`,
    };
  }
}

export async function testEndpoint(toolName: string): Promise<{
  success: boolean;
  tool: string;
  response?: any;
  error?: string;
}> {
  const token = env("XANO_METADATA_TOKEN");

  // Map common tool names to Xano API endpoints for direct testing
  const toolEndpoints: Record<string, string> = {
    me: "/api:e6emygx3/me",
    "slack-channels": "/api:e6emygx3/slack-channels",
    "calendar-events": "/api:e6emygx3/calendar-events",
    contacts: "/api:e6emygx3/contacts",
    "linkedin-profile": "/api:e6emygx3/linkedin-profile",
  };

  const endpoint = toolEndpoints[toolName];
  if (!endpoint) {
    return {
      success: false,
      tool: toolName,
      error: `Unknown tool "${toolName}". Known tools: ${Object.keys(toolEndpoints).join(", ")}`,
    };
  }

  try {
    const res = await fetch(`${XANO_BASE}${endpoint}`, {
      headers: { Authorization: `Bearer ${token}` },
      signal: AbortSignal.timeout(15000),
    });
    const data = await res.json();
    return {
      success: res.ok,
      tool: toolName,
      response: data,
    };
  } catch (err: any) {
    return {
      success: false,
      tool: toolName,
      error: err.message,
    };
  }
}

// --- CLI ---

if ((() => { try { return import.meta.url === `file://${realpathSync(process.argv[1])}`; } catch { return false; } })()) {
  (async () => {
    const [, , cmd, ...args] = process.argv;

    switch (cmd) {
      case "health": {
        const result = await checkHealth();
        console.log(`Healthy: ${result.healthy}`);
        console.log(`Status: ${result.status}`);
        console.log(`SSE reachable: ${result.sseReachable}`);
        console.log(result.message);
        break;
      }
      case "test": {
        const [tool] = args;
        if (!tool) { console.error("Usage: api.ts test <tool>"); process.exit(1); }
        const result = await testEndpoint(tool);
        if (result.success) {
          console.log(`Tool "${tool}" OK`);
          console.log(JSON.stringify(result.response, null, 2));
        } else {
          console.error(`Tool "${tool}" FAILED: ${result.error}`);
        }
        break;
      }
      default:
        console.log("Usage: npx tsx api.ts [health|test] ...");
    }
  })();
}

scripts- helper scripts it can run

prose-only skill - 1 inline code block live in SKILL.md above (no state/bin/ sidecar yet).

how we check it- the checks, plus the last 10 runs

rubric shape schema-shape check (no inline rubric)
recent mean 1.00 · 10 runs actor/auditor: unverifiable
deps none declared
timestamp verb score primary_issue artifact
2026-04-25 04:11Z - 1.00 - -
2026-04-21 15:59Z - 1.00 - -
2026-04-21 15:57Z - 1.00 - -
2026-04-21 03:53Z - 1.00 - -
2026-04-25 04:11Z - 1.00 - -
2026-04-21 15:59Z - 1.00 - -
2026-04-21 15:57Z - 1.00 - -
2026-04-21 03:53Z - 1.00 - -
2026-04-25 04:11Z - 1.00 - -
2026-04-21 15:59Z - 1.00 - -