earl
Secure CLI proxy for AI agents — HCL-defined operation templates with OS keychain secrets, MCP integration, and prompt injection protection
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/mathematic-inc--earl)HTML
<a href="/listings/mathematic-inc--earl"><img src="/api/listings/mathematic-inc--earl/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
These steps run a script from the network that findsafeskills does not scan.
# 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](https://mathematic-inc.github.io/earl/docs/quick-start/) for the full walkthrough, or [Agent-Assisted Setup](https://mathematic-inc.github.io/earl/docs/agent-assisted-setup/) to let an agent handle the install and configuration.
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 96 lines · 1 finding marked
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- <p align="center">
- <img src="site/public/social-preview.jpg" alt="Earl - AI-safe CLI for AI agents" width="100%" />
- </p>
- [](https://github.com/mathematic-inc/earl/actions/workflows/ci.yml)
- [](https://crates.io/crates/earl)
- [](LICENSE)
- 
- 
- 
- 
- 
-  
- [](https://github.com/mathematic-inc/earl/releases/latest)
- [](https://github.com/mathematic-inc/earl/releases/latest)
- [](https://github.com/mathematic-inc/earl/releases/latest)
- 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.
- **[→ Documentation](https://mathematic-inc.github.io/earl/)**
- ## Quick start
- ```bash
- # Install
- curl -fsSL https://raw.githubusercontent.com/mathematic-inc/earl/main/scripts/install.sh | bash
- Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
- Line 29 on GitHub
- # 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:
- ```json
- {
- "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](https://mathematic-inc.github.io/earl/docs/quick-start/) for the full walkthrough, or [Agent-Assisted Setup](https://mathematic-inc.github.io/earl/docs/agent-assisted-setup/) to let an agent handle the install and configuration.
- ## 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](https://mathematic-inc.github.io/earl/docs/how-earl-works/) for the full security model.
- ## Documentation
- - [Introduction](https://mathematic-inc.github.io/earl/docs/) — why Earl exists, how the security model works
- - [Quick Start](https://mathematic-inc.github.io/earl/docs/quick-start/) — install, first call, MCP config in five steps
- - [Template Schema](https://mathematic-inc.github.io/earl/docs/template-schema/) — field-by-field reference
- - [Secrets & Auth](https://mathematic-inc.github.io/earl/docs/secrets-and-auth/) — OS keychain storage, OAuth2 flows
- - [External Secrets](https://mathematic-inc.github.io/earl/docs/external-secrets/) — 1Password, Vault, AWS, GCP, Azure
- - [MCP Integration](https://mathematic-inc.github.io/earl/docs/mcp/) — stdio and HTTP transport, full vs. discovery mode
- - [Policy Engine](https://mathematic-inc.github.io/earl/docs/policy-engine/) — JWT auth and access control for HTTP deployments
- - [Environments](https://mathematic-inc.github.io/earl/docs/environments/) — production, staging, and per-environment overrides
- - [Hardening](https://mathematic-inc.github.io/earl/docs/hardening/) — SSRF protection, egress allowlist, production checklist
- - [Commands](https://mathematic-inc.github.io/earl/docs/commands/) — complete CLI reference
- - [Troubleshooting](https://mathematic-inc.github.io/earl/docs/troubleshooting/) — keychain errors, template validation, MCP issues
- ## Contributing
- Start with a [Discussion](https://github.com/mathematic-inc/earl/discussions/new),
- 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](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](https://github.com/sponsors/mathematic-inc).
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.