Back to Home
Hmbown icon

aleph

Verified Safe

by Hmbown

Overview

Aleph is an MCP server that provides LLMs programmatic access to gigabytes of local data without consuming context, implementing the Recursive Language Model (RLM) architecture.

Installation

Run Command
aleph

Environment Variables

  • ANTHROPIC_API_KEY
  • OPENAI_API_KEY
  • OPENAI_ORG_ID
  • ALEPH_PROVIDER
  • ALEPH_MODEL
  • ALEPH_SUB_MODEL
  • ALEPH_MAX_TOKENS
  • ALEPH_MAX_COST
  • ALEPH_MAX_ITERATIONS
  • ALEPH_MAX_DEPTH
  • ALEPH_MAX_WALL_TIME
  • ALEPH_MAX_SUB_QUERIES
  • ALEPH_SUB_QUERY_BACKEND
  • ALEPH_SUB_QUERY_API_KEY
  • ALEPH_SUB_QUERY_URL
  • ALEPH_SUB_QUERY_MODEL
  • ALEPH_TOOL_DOCS

Security Notes

The project explicitly implements a 'best-effort' sandboxed Python REPL (`exec_python`) which blocks common dangerous operations (filesystem, network, subprocess, dunder access, eval/exec/compile). Action tools (`run_command`, `read_file`, `write_file`) that interact with the filesystem or execute shell commands are gated by an `--enable-actions` flag, workspace scoping (`--workspace-mode`), and optional `--require-confirmation`. Sub-query functionality can launch CLI tools (e.g., `claude`, `codex`) or make external API calls, which are inherently external interactions. No hardcoded secrets were identified. The security design is transparent and offers control to the user, but the inherent nature of running arbitrary code or commands necessitates user vigilance and stronger external isolation for untrusted inputs.

Similar Servers

Stats

Interest Score92
Security Score8
Cost ClassLow
Avg Tokens1000
Stars70
Forks10
Last Update2026-01-19

Tags

RLMLLMContext ManagementCode ExecutionData Analysis