Earl
Enables secure retrieval of secrets from 1Password for use in template operations.
Allows executing GitHub API operations, such as searching repositories, via HCL templates.
Allows executing GraphQL API queries and mutations via HCL templates.
Enables secure retrieval of secrets from HashiCorp Vault for use in template operations.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
 
Earl sits between agents and external services. Operations are HCL files committed to your repository. The LLM sees a tool name and description; it never reads the template body. An injected instruction in an API response has nowhere to land because the LLM isn't reading the part of the request that executes.
Secrets stay in the OS keychain. They aren't in tool arguments, tool descriptions, or output.
Quick start
# Install
curl -fsSL https://raw.githubusercontent.com/mathematic-inc/earl/main/scripts/install.sh | bash
# Import a provider template
earl templates import https://raw.githubusercontent.com/mathematic-inc/earl/main/examples/3p/github.hcl
# Store a secret — prompts for the value, not echoed
earl secrets set github.token
# Call a command
earl call --yes --json github.search_repos --query "language:rust stars:>100"To use Earl as MCP tools in your agent, add it to your MCP config and restart. Claude Code and Cursor use the same format:
{
"mcpServers": {
"earl": {
"command": "earl",
"args": ["mcp", "stdio"]
}
}
}MCP tools don't activate until after restart. In the current session, use earl call --yes --json through the Bash tool.
See Quick Start for the full walkthrough, or Agent-Assisted Setup to let an agent handle the install and configuration.
Related MCP server: SecretVault MCP
How it works
You write an HCL template describing an operation: method, URL, auth, parameters. When an agent calls the tool, Earl loads the template, reads the required secret from the OS keychain, renders the Jinja expressions against the agent's supplied values, and executes the request. The LLM only ever provided parameter values. Every other part of the request — the URL, the auth header, the method — was written by a human and committed to the repo.
See How Earl Works for the full security model.
Documentation
Introduction — why Earl exists, how the security model works
Quick Start — install, first call, MCP config in five steps
Template Schema — field-by-field reference
Secrets & Auth — OS keychain storage, OAuth2 flows
External Secrets — 1Password, Vault, AWS, GCP, Azure
MCP Integration — stdio and HTTP transport, full vs. discovery mode
Policy Engine — JWT auth and access control for HTTP deployments
Environments — production, staging, and per-environment overrides
Hardening — SSRF protection, egress allowlist, production checklist
Commands — complete CLI reference
Troubleshooting — keychain errors, template validation, MCP issues
Contributing
Start with a Discussion, not a pull request. A Mathematic maintainer will review the proposal. If we decide to implement it, a maintainer or one of our AI agents will open the pull request. GitHub restricts pull request creation to Mathematic maintainers and repository collaborators with write, maintain, or admin access, plus authorized maintenance agents.
When Mathematic implements a proposal, the implementation pull request will link to the Discussion and credit the proposal's original author.
See CONTRIBUTING.md for the full policy.
License
Apache-2.0
This project is free and open-source work by a 501(c)(3) non-profit. If you find it useful, please consider donating.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Governed access to sensitive data, secrets and APIs for AI agents. A signed proof for each decision.
Deterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.
Real-time MCP & A2A prompt-injection, jailbreak, and tool-schema poisoning firewall for AI agents.
Security gateway for AI agents: policy, approval, and audited execution, no secrets shared.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to securely access authenticated services (HTTP, SSH, SMTP) without exposing secrets, by acting as a server-side proxy that injects authentication.MIT
- AlicenseNot gradedqualityBmaintenanceBounded egress gateway & secret proxy for AI agents and applications, enabling safe credential injection into upstream requests while keeping raw secrets out of LLM prompt contexts.MIT
- AlicenseAqualityCmaintenanceEnables AI agents to make authenticated API calls and run commands with secrets injected, while keeping credentials completely hidden from the model, with policy enforcement, grants, and audit logging.6MIT
- AlicenseAqualityCmaintenanceEnables AI agents to run shell commands, perform sandboxed file operations, and make HTTP requests through zero-trust guards that block command injection, path traversal, and SSRF while redacting secrets from inputs and outputs. Circuit breakers, per-session rate limits, and an append-only audit ledger prevent runaway loops, excessive token spend, and provide post-hoc traceability.5MIT