id.wispera
Passport & visa system for AI agent credentials. Detect, classify, and govern API keys, tokens, and secrets across MCP, OpenAI, Anthropic, LangChain, and more. Encrypted vault, policy engine, audit trails, delegation chains. Drop-in MCP server replaces plaintext credential storage.
claude mcp add --transport stdio gecochief-id.wispera npx -y @id-wispera/mcp-server
How to use
ID Wispera provides a native MCP server for AI agent credential governance. The server implements the Model Context Protocol (MCP) to allow clients and agents to request, manage, and audit credentials (passports and visas) across platforms. With the MCP server running, you can onboard and coordinate credential provisioning, enforce policy-driven access controls, detect and track credential usage, and traverse delegation chains between agents and humans. The server is designed to interoperate with the surrounding Wispera toolkit, including the core governance engine for detection, auditing, and location provisioning, and can integrate into LangChain, OpenAI Agents SDK, and other agent frameworks via MCP events and RPC-style calls. You can connect your AI agents or tooling to the MCP server to request credentials, validate permissions, and log actions for audit trails.
Typical workflows include: starting the MCP server, registering or importing credentials as passports, attaching visas to define permitted actions, performing delegation as needed, and querying the audit trail to trace credential usage. The server exposes endpoints and protocol hooks that client libraries can consume, enabling automated credential lifecycle management within your agent ecosystem. By centralizing credential governance, ID Wispera helps provide visibility, policy enforcement, and secure sharing for AI agents across OpenClaw, cloud providers, and software integrations.
How to install
Prerequisites:
- Node.js (LTS) and npm installed on your system
- Git installed for cloning or accessing the repository
- Basic familiarity with npm workspaces or monorepos (optional but helpful)
Installation steps:
-
Install Node.js and npm if you haven’t already
- visit https://nodejs.org/ and install the LTS build
-
Install the MCP server package from the Wispera monorepo
- If you are consuming from npm registry (recommended in most setups): npm install @id-wispera/mcp-server
- Alternative: clone the repository and install locally: git clone https://github.com/gecochief/id.wispera.git cd id.wispera/packages/mcp-server npm install npm run build
-
Build the MCP server (if building from source) npm run build
-
Run the MCP server
- From distribution: npx -y @id-wispera/mcp-server
- From local build: node dist/server.js (or the entry point defined by the package)
-
Verify the server is running
- Check logs for MCP server readiness messages
- Use the client library or curl requests to interact with MCP endpoints
Notes:
- If you are integrating into an orchestration or CI/CD, consider containerizing the MCP server for reproducible deployments.
Additional notes
Tips and common issues:
- Environment variables: you may need to configure security keys, vault paths, and provider credentials. Use env vars like WISPERA_VAULT_PATH, WISPERA_VAULT_KEY, and PROVIDER_CREDENTIALS as placeholders until documented by your deployment.
- MCP compatibility: ensure clients use the MCP protocol version supported by the server. Align client libraries with the server’s MCP spec to avoid protocol mismatches.
- Audit and policy tuning: leverage the Policy Engine and Audit Trail features to tailor credential access controls and monitoring. Start with a minimal policy set and expand as you validate workflows.
- Network security: run the MCP server behind TLS termination in production and rotate credentials regularly. Restrict access to trusted agents and human operators.
- Debugging: enable verbose logging in development to surface MCP negotiation and passport/visa lifecycle events for easier troubleshooting.
Related MCP Servers
bytebot
Bytebot is a self-hosted AI desktop agent that automates computer tasks through natural language commands, operating within a containerized Linux desktop environment.
gaianet-node
Install, run and deploy your own decentralized AI agent service
nono
Secure, kernel-enforced sandbox CLI and SDKs for AI agents. Capability-based isolation with secure key management, atomic rollback, cryptographic immutable audit chain of provenance. Run your agents in a zero-trust environment.
agenite
🤖 Build powerful AI agents with TypeScript. Agenite makes it easy to create, compose, and control AI agents with first-class support for tools, streaming, and multi-agent architectures. Switch seamlessly between providers like OpenAI, Anthropic, AWS Bedrock, and Ollama.
diy-tools
An MCP server that allows users to dynamically add custom tools/functions at runtime
cortex-ast
A powerful Model Context Protocol (MCP) server and Omni-AST engine. It empowers AI agents to seamlessly parse complex codebases, execute secure cross-project operations, and dynamically fetch token-optimized rules.