aleph-mcp-core

aleph-mcp-core is a cursor rule for Cursor from Sourcery-info/barracuda-mcp. It costs 337 tokens per session, scanned A, original, MIT.

A set of rules for building an MCP server, a program that gives an AI assistant structured tools, with OpenAleph integration and safe handling of credentials.

In plain words
What is it for?
Use it when implementing or testing barracuda-mcp tools such as OpenAleph search and entity retrieval.
Why use it?
It provides consistent tool registration, input validation, error handling, testing, and secret redaction practices.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it when implementing or testing barracuda-mcp tools such as OpenAleph search and entity retrieval.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/sourcery-info/barracuda-mcp/aleph-mcp-core
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/Sourcery-info/barracuda-mcp

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for aleph-mcp-core

README.md
[![agentmods](https://agentmods.dev/badge/rules/sourcery-info/barracuda-mcp/aleph-mcp-core/github.svg)](https://agentmods.dev/rules/sourcery-info/barracuda-mcp/aleph-mcp-core)
Your own site
<a href="https://agentmods.dev/rules/sourcery-info/barracuda-mcp/aleph-mcp-core"><img src="https://agentmods.dev/badge/rules/sourcery-info/barracuda-mcp/aleph-mcp-core/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for aleph-mcp-core

Your own site · 80×15
<a href="https://agentmods.dev/rules/sourcery-info/barracuda-mcp/aleph-mcp-core"><img src="https://agentmods.dev/badge/rules/sourcery-info/barracuda-mcp/aleph-mcp-core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 337 This file is loaded in full into every session.
When invoked 337 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00337 $0.00337
Opus 5 $0.00169 $0.00169
Sonnet 5 $0.00067 $0.00067
Haiku 4.5 $0.00034 $0.00034

Measured 8d ago against content hash 37ca84eec3c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

aleph-mcp-core scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/rules/aleph-mcp-core.mdc · 16 lines

What it actually says

barracuda-mcp core rules

  • Use the official @modelcontextprotocol/sdk patterns: McpServer, registerTool, and stdio transport for local Cursor use unless explicitly building a remote HTTP server.
  • Validate all tool inputs with Zod; keep schemas as the single source of truth and reuse them for registerTool inputSchema where possible.
  • Never log API keys, Authorization headers, or raw credential-bearing config. Redact errors that might echo secrets.
  • Keep HTTP access behind AlephClient (or a small dedicated module). Inject fetch (or Pick<AlephClient, "search">) in tests instead of calling production OpenAleph.
  • Map OpenAleph failures to MCP tool results with isError: true and a clear text message; include HTTP status and JSON body when safe.
  • OpenAleph auth for REST: Authorization: ApiKey <key> and optional X-Aleph-Session, matching the official Python client behavior.
  • Prefer small, pure helpers (URL building, env parsing) that are easy to unit test.
  • Expose OpenAleph via tools: aleph_search (/api/2/search), aleph_get_entity (/api/2/entities/:id), and aleph_get_entity_markdown (full Email Markdown or Pages plain text when structured output was truncated); keep structured response behavior documented in README.md and prompts/.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 16 lines · 337 tokens per session scan A 37ca84eec3c5

Subscribe to this mod's changes

aleph-mcp-core is a cursor rule published in the GitHub repository Sourcery-info/barracuda-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 337 tokens to every session, about $0.0017 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.