converse
Verified Safeby FallDownTheSystem
Overview
The server provides a multi-model conversational AI agent capable of general chat, collaborative thinking, and a consensus mechanism for complex technical decisions, particularly geared towards development assistance and code analysis.
Installation
npx converseEnvironment Variables
- OPENAI_API_KEY
- XAI_API_KEY
- GOOGLE_API_KEY
- ANTHROPIC_API_KEY
- MISTRAL_API_KEY
- DEEPSEEK_API_KEY
- OPENROUTER_API_KEY
- CODEX_API_KEY
- GOOGLE_CLOUD_PROJECT
- GOOGLE_CLOUD_LOCATION
- MCP_TRANSPORT
- PORT
- HOST
- LOG_LEVEL
- MAX_MCP_OUTPUT_TOKENS
- ASYNC_MEMORY_TTL_MS
- ASYNC_CACHE_DIR
- ASYNC_DISK_TTL_MS
- DEBUG
- NODE_ENV
- CODEX_SANDBOX_MODE
- CODEX_SKIP_GIT_CHECK
- CODEX_APPROVAL_POLICY
Security Notes
The server uses external SDKs (Codex, Gemini CLI, Claude SDK) that execute local binaries. While these SDKs have their own sandbox and approval policies, their security is external to this codebase and could pose a high risk if the underlying CLI is compromised or manipulated by user input. The `clientCwd` parameter, derived from the user's working directory, is used for file access and agent execution, potentially allowing interaction with sensitive files or execution outside the intended scope if not properly sandboxed by the underlying SDKs. However, the `httpTransport` component implements good network security practices including configurable CORS, request timeouts, rate limiting, and DNS rebinding protection. Path traversal for export directories is mitigated using `path.basename`.
Similar Servers
claude-flow
Orchestrates AI agents (Claude) for development workflows, including code generation, testing, analysis, research, and project migration, with MLOps capabilities.
1xn-vmcp
An open-source platform for composing, customizing, and extending multiple Model Context Protocol (MCP) servers into a single logical, virtual MCP server, enabling fine-grained context engineering for AI workflows and agents.
consult-llm-mcp
Facilitates Claude Code to consult powerful external AI models for complex code analysis, debugging, and review tasks.
claude-faf-mcp
Provides AI-optimized context for software projects to large language models, enhancing collaboration and project understanding via 50+ specialized tools within Claude Desktop workflows.