# io.github.GavinLee1/mcp-fleet

> 12 MCP tools: invoice→JSON, text→SQL, PII redaction, regex & more. Free to try, pay per call.

- name: io.github.GavinLee1/mcp-fleet
- version: 0.3.0
- connection class: R0 (autonomous)
- trust: 68/100 flags: no-repository
- quality: 70/100 (needs work)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.GavinLee1%2Fmcp-fleet
- tools: https://api.protogrid.dev/v1/servers/io.github.GavinLee1%2Fmcp-fleet/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "mcp-fleet": {
      "type": "sse",
      "url": "https://mcp-fleet.nebula-labs.online/mcp/sse?src=mcp_registry",
      "headers": {
        "Authorization": "Bearer ${MCP_FLEET_TOKEN}"
      }
    }
  }
}
```

Placeholders to fill: `${MCP_FLEET_TOKEN}`.

## Trust

- hygiene: 80
- liveness: 96
- freshness: 65
- provenance: 35
- drivers: +reachable +uptime-90% ~updated-119d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 70/100 (needs work)

### protocol: 50 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- warn `protocol.transport`: only the legacy HTTP+SSE transport, deprecated until 2027-07-28
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: json_schema_infer (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); text_to_compliance_checklist (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); meeting_summarize (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 1,006 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 12, about 1,006 tokens to load them all
- tool set hash: a7d99f4a1b085082e2da23c3cb692b43
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.GavinLee1/mcp-fleet.svg)](https://protogrid.dev/servers/io.github.GavinLee1/mcp-fleet)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://mcp-fleet.nebula-labs.online/mcp/sse?src=mcp_registry (sse, auth none, reachable true, uptime30d 0.89908254)

## Packages

_none_

## Tools (12)

- `code_explain`: Explain what a code snippet does, step by step, with complexity and risk notes.
- `cron_explain`: Explain a cron expression in plain English and list the next run times.
- `email_draft`: Turn bullet points or a brief into a polished professional email (subject + body).
- `invoice_pdf_to_json`: Convert raw invoice text (extracted from PDF, email, or image OCR) into a structured JSON object. Returns vendor, date, line items, totals, and currency in a machine-readable format.
- `json_schema_infer`: Infer a JSON Schema (draft 2020-12) from a sample JSON document.
- `meeting_summarize`: Summarize a meeting transcript into a summary, action items, decisions, and participants.
- `pii_redact`: Locally detect and redact high-confidence PII (emails, phones, SSNs, credit cards, IPs) from text — raw data never leaves the server. Returns redacted text and found entities.
- `regex_builder`: Build a regular expression from a plain-language description, with an explanation and test cases.
- `sentiment_analyze`: Analyze sentiment of text with an overall score and per-aspect breakdown.
- `text_to_compliance_checklist`: Convert a block of requirement, regulation, or specification text into a structured compliance checklist. Each checklist item includes a category, obligation, priority (HIGH/MEDIUM/LOW), and verification method.
- `text_to_sql`: Convert a natural-language data question into a SQL query. Returns the SQL, dialect, and tables used.
- `unit_test_outline`: Generate a unit-test outline (cases + coverage targets) for a function.