BotShelf Vampire BOTSHELF VAMPIRE Register

Library · Team · MCP · data-analysis

MCP mcp Analytics Untested tool-protocol free

Data Analysis — MCP

Summarize pasted tables or CSV snippets into findings, caveats, and what to check next. Analysis only. (MCP-oriented tool + prompt pack (read-only first).)

Id: mcp/data-analysis · Slug: data-analysis · Status: Untested · Untested on this machine — recipe reviewed for safety (no secrets, no destructive commands, no auto-spend). Mark tested after you run it locally.

What is this

MCP for MCP. Summarize pasted tables or CSV snippets into findings, caveats, and what to check next. Analysis only. (MCP-oriented tool + prompt pack (read-only first).)

How this runtime fits

This MCP pack is an MCP integration / tool-enabled agent surface for the parent AI Team. Multi-agent language applies only when a host actually composes multiple agents around these tools.

Parent AI Team: data-analysis · What is an AI Team?

What it does

Summarize pasted tables or CSV snippets into findings, caveats, and what to check next. Analysis only. (MCP-oriented tool + prompt pack (read-only first).)

Who for

Builders working on Analytics jobs who can run MCP themselves.

Need to run

How to use

  1. Review server_hints.md and implement only allowlisted read-only tools.
  2. Load prompt.md as the client system prompt.
  3. Run one Example in query with tools off; then enable library_search only.
  4. Confirm path allowlist before any file read tool.

Limitations

Test status

Status: Untested · Untested on this machine — recipe reviewed for safety (no secrets, no destructive commands, no auto-spend). Mark tested after you run it locally.

# MCP pack — Data Analysis

## prompt.md (client)
You are a data analysis desk. Goal: findings from pasted numbers only.

RULES:
- Do not invent rows. If math is approximate, say so.
- Call out sample size, missing fields, and selection bias.
- No trading/investment advice. No auto-spend recommendations.
- Charts described in text only unless user provides image.

OUTPUT:
1) Dataset snapshot
2) Key findings (max 7)
3) Caveats
4) Next checks / cuts to request

## server_hints.md
Expose only read-only tools for stage 1, for example:
- `library_search` — search local catalog snippets the user installed
- `fetch_local_file` — read a path under an allowlisted directory

Tool design rules:
- No tool that sends email, posts to social, or charges payment.
- No tool that reads `~/.ssh`, `.env`, or browser cookie DBs.
- Arguments must be schema-validated; reject path traversal.
- Log tool calls for the human operator.

Example tool schema (illustrative JSON):
```json
{
  "name": "library_search",
  "description": "Search local BotShelf library snippets",
  "inputSchema": {
    "type": "object",
    "properties": {
      "query": {"type": "string", "minLength": 1, "maxLength": 200}
    },
    "required": ["query"]
  }
}
```

Wire this pack into an MCP-aware client with tools disabled until the allowlist is reviewed.
Paste:
day,signups,paid
Mon,40,2
Tue,38,1
Wed,22,1
Thu,21,0
Fri,25,1
Note: Wed deploy.
Snapshot: 5 weekdays; Wed deploy coincides with signup drop.
Findings: Signups fell ~45% Wed–Thu vs Mon–Tue; paid sparse (n small).
Caveats: one week; no traffic denominator.
Next: traffic + error logs around deploy.

Protocol-level pack. Prefer read-only tools. Never ship credentials inside MCP configs.

Parent: data-analysis · implementation_id: mcp/data-analysis

teams/data-analysis/mcp · commit eb87e8e049fdf9908e438305ff827c7b617505b5 · license: free-use-at-own-risk

Structural check: PASS · env: structural (structural only — does not set Verified)

Soft thematic links only — not identity merges. Marketplace Teams ≠ Library AI Team records.