emisar

emisar

Leave the agent working. Keep production authority bounded.

emisar gives AI agents remote access to infrastructure through CLI or MCP. You choose the actions they can use. Your policy decides what runs automatically, what needs approval, and what is denied. A small runner connects out from each host and checks every request before running it. Agents call these actions without receiving a general production shell.

Start with the public pack catalog and let emisar suggest the packs that match a host. Add your own actions without adding another MCP server to every client.

Start with one host

You need an emisar account, a Linux host with systemd, and sudo. GitHub CLI with gh attestation verify --bundle checks the release signature. Without GitHub CLI, the installer asks before it continues with only the checksum. With --yes, it warns and continues. Allow outbound HTTPS to emisar.dev:443, registry.emisar.dev:443, tuf-repo-cdn.sigstore.dev:443, and tuf-repo.github.com:443. The last two serve the public trust roots used to authenticate release checksums. No GitHub login is required.

GitHub is the optional release fallback. If you want that fallback, also allow api.github.com:443, github.com:443, and release-assets.githubusercontent.com:443.

1. In the console, choose Connect a runner. Copy the generated command; it contains a fresh, single-use enrollment key.
2. Run it on the host:

   curl -fsSL https://emisar.dev/install.sh \

| sudo EMISAR_ENROLLMENT_KEY=emkey-enroll-... bash

The installer authenticates the signed release checksum and verifies the archive against it. It then creates the service, installs host-matched starter packs, and starts the runner.

1. Confirm the runner is online in the console, then dispatch linux.uptime with a reason. You are done when the output appears and the run is present in the audit trail.
2. Open AI agents and connect your client. Remote MCP clients use OAuth; local stdio clients can use the emisar-mcp bridge and its browser approval flow. Agents that work in a terminal can also call tools directly with the emisar-mcp CLI.

The complete walkthrough, including expected output and troubleshooting, is at emisar.dev/docs/quickstart. An agent can perform and certify the setup with the public install-emisar skill.

How an action runs

AI client

| CLI or MCP: discover actions, request one with typed arguments v emisar control plane | authenticate, scope, apply policy, wait for approval when required v outbound-only runner | verify pack hash, validate arguments, enforce local limits v declared host command stream redacted output, journal the attempt, update fleet audit

The action pack defines the contract: the executable, argv shape, argument schema, risk, timeout, output limits, redaction, and side-effect description. The model selects from that contract; it does not invent a command line for the runner to execute.

Adding a pack adds capabilities behind the same MCP surface. Operators do not need to deploy another tool server or reconfigure every agent when the catalog changes.

What holds the boundary

• The runner opens an outbound TLS WebSocket and exposes no inbound listener. Commands return through that established connection.
• Cloud input is limited to declared actions and typed, schema-bounded arguments. The runner rejects unknown actions and arguments.
• Packs are content-addressed: a hash of their contents identifies them. The control plane pins the trusted pack hash, and the runner recomputes it from disk before execution. New or changed custom packs wait for trust.
• The control plane evaluates runner scope, risk policy, action overrides, standing grants, and conditional approval before dispatch.
• On the host, the runner clamps execution options to the pack's limits and runs the declared binary and argv. The runner redacts output before it leaves the host, and Emisar keeps the redacted output in run history.
• The control-plane audit includes denied and pending requests. Every runner also writes its execution attempts and local refusals to a hash-chained JSONL journal.
• A runner can optionally require bridge-attested dispatch: intent signed by the customer-authorized MCP bridge with an Ed25519 or ECDSA P-256 leaf key. The control plane then cannot invent or widen a permitted call.

Read the exact guarantees, limitations, and threat model in .agent/kb/specs/security-model.md.

How emisar fits into your stack

Use declared actions for agent access and SSH for interactive administration. Run the agent in a sandbox such as co:op, grant the runner the OS permissions its actions need, and ship lasting configuration changes through your deployment workflow.

The runner executes permitted actions with its service user's OS permissions; it does not isolate those processes. Permitted destructive actions still have real effects. Review action definitions, pack trust, policy, runner settings, and host permissions together when deciding what the agent may do.

The staging-only shell pack is the explicit break-glass (emergency-only) exception to the declared-action model. It is critical-risk, default-denied, never suggested, and should not be installed on production runners.

Find the right surface

Repository layout

portal/   Elixir/Phoenix control plane, operator console, website, and MCP API

runner/ Go host runner and operator CLI mcp/ Go stdio-to-HTTP MCP bridge packs/ Versioned action-pack catalog skills/ Standalone customer skills for coding agents infra/ Production Terraform for emisar on Google Cloud run Root contributor command for development, tests, gates, and operations dev/ Development Compose topologies, images, configs, and fixtures tools/ Go implementations behind the contributor command and CI dist/ Tracked distribution packages plus ignored generated build output .agent/kb/ Repository architecture, specifications, runbooks, and rules

Each top-level project has its own AGENTS.md with its architecture, security rules, and verification gate. Run ./run help for the complete list of contributor commands.

Develop locally

The recommended path needs only Coop and Docker on the host. It installs every tool version the repository pins in the isolated project image:

./run bootstrap             # works before Go is installed

coop build # build the pinned project image once coop run -- ./run setup # sidecars, deps, migrations, browser tooling coop shell # enter the development box

Then, inside the shell:

./run seed        # explicit, idempotent demo data

./run serve # live reload at the URL printed by Coop

or: ./run serve --iex

For native development, install the exact versions in .tool-versions with asdf. You also need Git, Coop, Docker, the PostgreSQL client, ShellCheck, jq, GNU Bash (with read -N), GNU coreutils, Chrome/Chromium, and ImageMagick. On macOS, Apple's bundled Bash and BSD utilities cannot run all pack regression checks:

brew install bash coreutils jq

export PATH="$(brew --prefix coreutils)/libexec/gnubin:$(brew --prefix bash)/bin:$PATH"

./run setup checks all prerequisites before starting services; ./run doctor reports every detected version and any mismatch to fix. On macOS, run ./run certs trust once for this workspace after setup.

The fast loop runs Phoenix in the current environment and keeps only PostgreSQL and Keycloak in the workspace-isolated Coop dependency stack.

./run urls prints this workspace's distinct Portal, metrics, Postgres, and Keycloak URLs. Coop forks inherit the same setup but receive different ports and volumes. Setup, serve, and reset never apply seeds unless you ask for them.

Use ./run status for a read-only view of the current workspace, ./run logs [db|keycloak] for its exact sidecar logs, and ./run psql for its development database. Every canonical gate (./run gate ) prints its current phase and elapsed time; a failure names the phase that stopped it.

The root docker-compose.yml remains the slower packaged topology with the release Portal image, seeded demo data, three runners, MCP, and signing. Start it with ./run smoke; it serves http://localhost:4010. See portal/README.md and dev/README.md.

License

This repository is dual-licensed:

• runner/, mcp/, packs/, skills/, and dist/cursor-plugin/ are open source under the Apache License 2.0; the skills and the Cursor plugin carry their own copy (skills, plugin). You can inspect, build, package, and operate the on-host components independently.
• Everything else, including portal/, is source-available under the Business Source License 1.1. Non-production use is free. Production use is permitted only as needed to operate the Apache-licensed components or the hosted service under the Additional Use Grant. Other production use requires a commercial license. Each version converts to Apache 2.0 on its Change Date.

See contributing, security, and the CLA. For commercial licensing, contact licensing@emisar.dev.