Six-gate governance for AI agents: PROCEED/PAUSE/HALT decisions with hash-chained audit trails.
Aegis MCP server exists for a simple reason — assistants are far more useful when they can act on Aegis directly instead of describing what you should do. Six-gate governance for AI agents: PROCEED/PAUSE/HALT decisions with hash-chained audit trails.
Give your agent a decision gate it can call before it acts — and an audit record compliance can actually read (NIST AI RMF, EU AI Act Annex IV).
Once Aegis is connected, these are the calls the assistant has available:
aegis_evaluate_proposal — Full six-gate evaluation of a proposal; returns PROCEED/PAUSE/HALT/ESCALATE with per-gate scores and rationaleaegis_quick_risk_check — Fast risk screen for a proposed changeaegis_check_thresholds — Current gate threshold configurationaegis_get_scoring_guide — Domain-specific guidance for deriving gate parameters (e.g. cicd)aegis_record_proposal — Record a proposal for later verificationaegis_list_proposals — List recorded proposalsaegis_verify_proposals — Verify recorded proposals against outcomesaegis_list_decisions — List past governance decisionsaegis_get_decision — Fetch a specific decision with full audit detailaegis_crypto_status — Hash-chain audit integrity statusBeing a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
You will need 2 environment variables: AEGIS_API_KEY, YOUR_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Aegis's toolset — aegis_evaluate_proposal, aegis_quick_risk_check, aegis_check_thresholds and 7 more — is a fair guide to whether it matches your workflow. It is maintained by com.undercurrentholdings; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Aegis's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| aegis_evaluate_proposal | Full six-gate evaluation of a proposal; returns PROCEED/PAUSE/HALT/ESCALATE with per-gate scores and rationale |
| aegis_quick_risk_check | Fast risk screen for a proposed change |
| aegis_check_thresholds | Current gate threshold configuration |
| aegis_get_scoring_guide | Domain-specific guidance for deriving gate parameters (e.g. cicd) |
| aegis_record_proposal | Record a proposal for later verification |
| aegis_list_proposals | List recorded proposals |
| aegis_verify_proposals | Verify recorded proposals against outcomes |
| aegis_list_decisions | List past governance decisions |
| aegis_get_decision | Fetch a specific decision with full audit detail |
| aegis_crypto_status | Hash-chain audit integrity status |
{
"mcpServers": {
"aegis": { "command": "aegis-mcp-server" }
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| AEGIS_API_KEY | Credential the server authenticates with. | Yes |
| YOUR_API_KEY | Credential the server authenticates with. | Yes |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.