HecateBLOCK
AI workspace and runtime for projects, chats, providers, memory, approvals, and supervised agents.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
AI workspace and runtime for projects, chats, providers, and supervised agents. Run Hecate on your machine as the personal control plane for agent work: create projects, chat with models, supervise external agents, use Hecate from ACP-capable clients, approve risky actions, inspect diffs, and trace what happened.
Status: pre-1.0. Hecate is useful today as an AI workspace for model-provider routing, Hecate Chat, External Agent sessions, project-scoped work, approvals, artifacts, usage, and observability. It is not production-stable infrastructure yet: the bounded report-only QA runbook is available, while additional workflow modes, browser typing and visual capture, broader Work policy integrations, and sandbox hardening are still evolving work. Read [known limitations](docs/op
c69c6ffe7d51OBSERVED · 2026-10-10Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add hecate-website --env GITHUB_TOKEN=${GITHUB_TOKEN} -- npx -y [email protected]{
"mcpServers": {
"hecate-website": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"GITHUB_TOKEN": "${GITHUB_TOKEN}"
}
}
}
}Exposed tools (12)
11 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
Developer | read | Build product changes. |
Editor | read | Prepare the release narrative. |
GitHub | read | Read and link GitHub work. |
Hecate | read | |
Implementation | read | Make the code and documentation changes, then leave a concise evidence trail. |
Research | read | Durable research workspace. |
Researcher | read | Synthesize interview findings for review. |
Reviewer | read | Review the artifact evidence and call out release-risk follow-ups. |
plan | write | Create a plan |
proposal | read | Draft a Project Assistant proposal |
show_weather | read | Render a tiny weather dashboard MCP App. |
web | read | Search the web |
Trust audit
BLOCKgrade F · trust 45/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (8 observation(s))
- Network
- declared (6 observation(s))
- Shell
- declared (4 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (25)
"--frozen-intrinsics", "--heap-prof", "--insecure-http-parser", "--inspect", "--inspect-brk",
# HECATE_POSTGRES_URL=postgres://hecate:hecate@localhost:5432/hecate?sslmode=disable
gradle-wrapper.jar
icon.icns
# HECATE_ALLOWED_ORIGINS=http://127.0.0.1:5173,http://localhost:5173
# derives http://127.0.0.1:<port> from HECATE_ADDRESS. Set this when the listen
# HECATE_PUBLIC_URL=http://127.0.0.1:8765
PROVIDER_LLAMACPP_BASE_URL=http://127.0.0.1:8080/v1
PROVIDER_LMSTUDIO_BASE_URL=http://127.0.0.1:1234/v1
chatAttachmentSensitiveDSN = "postgres://private-user:[email protected]/hecate"
if cfg.Postgres.DatabaseURL != "postgres://hecate:hecate@localhost:5432/hecate?sslmode=disable" {const secret = "browser-setup-remote-secret-for-tests"
const secret = "DOGFOOD_PRIVATE_SENTINEL"
"codex": {token: "HECATE_CODEX_EMBEDDED_OK", fileToken: "HECATE_CODEX_FILE_OK"},"claude_code": {token: "HECATE_CLAUDE_EMBEDDED_OK", fileToken: "HECATE_CLAUDE_FILE_OK"},"cursor_agent": {token: "HECATE_CURSOR_ACP_OK", fileToken: "HECATE_CURSOR_FILE_OK"},.goreleaser.yaml
.lycheeignore
.oxfmtrc.json
.oxlintrc.json
.cargo_vcs_info.json
req := httptest.NewRequest(http.MethodGet, "/../../etc/passwd", nil)
Function: types.ToolCallFunction{Name: "read_file", Arguments: `{"path":"../../etc/passwd"}`},fileGroups: [../../src]
include_bytes!("../../../../website/public/brand/png/mark-trivium-black-32.png");Gates applied: no_behavioural_pass.
c69c6ffe7d51full audit observations/trust-audit/mcp-server/hecatehq__hecate-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-10 | c69c6ffe7d51 | BLOCK | F | 45 | first audit |
Questions
What is the Hecate MCP server?
AI workspace and runtime for projects, chats, providers, memory, approvals, and supervised agents.
What tools does Hecate expose?
12 in total: 11 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Hecate safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (45/100) and found 2 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does Hecate need?
It reads GITHUB_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Hecate run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on npm as hecate-website at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (c69c6ffe7d51), read on 2026-10-10. The repository is watched and re-audited when it changes.