Seahawk
Provides registered GUI observation and actuation for Aseprite windows, including screenshots, window/focus state, and gated focus, click, key chord, text entry, scroll, and drag actions.
Provides registered GUI observation and actuation for Blender windows, including screenshots, window/focus state, and gated focus, click, key chord, text entry, scroll, and drag actions.
Uses a local Ollama-served vision model for natural-language GUI grounding, returning an element bounding box and its derived center point for verified GUI actions.
Provides registered GUI observation and actuation for Unity Editor and Hub windows, including screenshots, window/focus state, and gated focus, click, key chord, text entry, scroll, and drag actions.
Authenticated broker for Epic's built-in Unreal Engine 5.8 MCP server, exposing a curated editor tool surface over stdio with token auth, read/write/execute classification, default-deny execute tools, op logging, and guarded forwarding to the local editor.
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.
Seahawk
The estate's authenticated broker for Unreal Engine's built-in MCP
server (Epic's ModelContextProtocol plugin in UE 5.8). Named for
Rafael Sabatini's The Sea Hawk (Owner, D-171; renamed from conn).
Epic's editor MCP server is powerful and completely unauthenticated: any local process that can reach its loopback port gets the editor's full tool surface, including in-editor Python execution. Seahawk exists so agents never touch that raw server. It serves modern-era MCP (2026-07-28) over stdio to agents, and downstream it speaks to Epic's legacy-era server as a client, localhost only.
Controls
Era guard + sequencer (fleet template): legacy
initializeis refused with the typed-32022; forwarded requests apply one settle at a time, in order, against the stateful editor session.Agent authentication: every
tools/callmust carry the agent token in_meta["seahawk/agent_token"]. The guard verifies it (SHA-256 digests, constant-time compare), strips it from the frame, and logs refusals. Missing/wrong token: typed-32001.Class curation: every downstream tool is classified read / write / execute from the verified S0 census of UE 5.8's surface (830 tools; see the build workspace's
SURFACE.md). Unclassified tools are withheld fromtools/listand refused on call.Execute default-deny: execute-class tools (in-editor Python, arbitrary file write, Blueprint compilation, plugin loading, PIE, UI input injection, settings persistence, skill authoring, …) are listed with destructive annotations but refused unless the operator enables the specific tool in policy and the call carries a distinct operator token in
_meta["seahawk/operator_token"].Op log: every brokered call and guard refusal appends one JSON line — tool, class, SHA-256 of the canonical arguments, outcome, downstream latency. Raw argument values are never logged. This is the non-idempotency record: exactly what was applied, in order.
Policy as data: tokens, downstream URL (loopback enforced), execute enablements, and per-tool class overrides live in a TOML config — see
seahawk.example.toml.
Related MCP server: unreal-mcp-ue4
Computer use (S4)
Beyond the Unreal broker, Seahawk drives GUI applications on
its own X11 display through a built-in provider. The class
lattice is read < write < actuate < execute; classification
follows reach, not mechanism (Epic's Slate UI-injection tools
stay execute for exactly that reason).
Registration is policy data only:
[[gui.apps]]entries in the config name an application and the window-match strings (WM_CLASS / instance equality, or title substring) that identify its windows. There is no agent-callable registration and no runtime re-registration; the config is read once at startup. The estate's media-GUI registrations ship inseahawk.example.toml: Blender, Unity (Editor + Hub), ComfyUI (browser-hosted; matched by window title), Aseprite.Per app, two tools:
gui.<app>.observe(read class — screenshot, window list, focus state; screenshots return a PNG and are op-logged by digest + dimensions, never by content) andgui.<app>.actuate(actuate class — focus, click, double-click, key chords, text entry, scroll, drag).Actuate is default-deny with the execute two-key rule: the tool must be named in
policy.actuate_enabledand each call must carry the operator token. Actuation is confined to the registered window's rectangle (coordinates are validated against it before anything is injected), and every actuation is bracketed by screenshots whose digests land in the op log alongside the target description — a click cannot be undone, so the record shows what the screen held on both sides of it.Honest caution: input into an application that hosts scripting (Blender's Python console, Unity's editor, Aseprite scripts, ComfyUI custom nodes) can compose into code execution through the UI. The actuate class records the mechanism; the two-key gate prices the risk. Treat enabling
gui.<app>.actuatewith the same gravity as enabling an execute-class tool for that application.
Vision grounding (S5, hardened by the 1.0 curative round)
Three broker-level tools give the broker eyes, gated by the
same decide() lattice as everything else (grounding is
perception only — it grants no permission):
gui.observe(read): a registered app's frame with display geometry, stored under its SHA-256; results carry the resolvedwindow_idand a blank-frame content verdict (content|suspect_blank).gui.ground(read): a natural-language target → the element's bbox plus the point derived as its centre, via a local Ollama-served vision model or the calling agent answering the broker's ticket. The centre is derived, never estimated — the curative fix for the S5 benchmark's trailing-edge aim bias.gui.act_verified(actuate): act and verify against a fresh capture. Thechangedcheck can be anchored (changed_around) or full-frame (full_frame); point-less actions diff the full frame by default. Retries change strategy (refined description, then route/crop escalation) and stop early on an identical re-ground. Frames that stay suspect-blank through a bounded content poll refuse the act (seahawk_gui_suspect_blank), and a caller may pinwindow_idagainst silent retargeting (seahawk_gui_window_mismatch). Visual verdicts follow the frozen Visual Benchmark v1 (BENCH-VISUAL.md).
Code feedback (D-230 wiring)
code.feedback (read) closes the loop between brokered
GUI work and the estate's language tooling: per file it returns
LSP diagnostics (theodolite headless route; GDScript via
periscope), lint verdicts and format changed flags
(periscope running diver's own pipelines — Seahawk consumes
the catalog live through periscope, never a second hardcoded
list), file hashes, and the catalog provenance. Calls are
bounded episodes (3 per workspace + file set per window; the
4th is refused with the last counts). A route that cannot
serve a check answers seahawk_tooling_unavailable — feedback
is never assumed clean, and it never writes: the tooling
client's dispatch table contains no apply/write call at all.
Wiring is opt-in policy data ([[tooling]] + [feedback] in
seahawk.example.toml).
Honest limits
Seahawk cannot firewall Epic's port: a local process that bypasses
Seahawk and speaks to the editor directly is outside its
guarantees. The operating discipline is lab-only use — throwaway
projects, editor up only during brokered sessions, nonstandard
port. The full threat model is in SURFACE.md.
Status
1.0.0 — lab-only (Owner ruling, D-146/D-169). The safety
charter is unchanged and binding: token auth, execute- and
actuate-class default-deny via decide(), append-only op log,
lab-only. Publication to crates.io / the MCP registry is held
for the Owner's word (see CHANGELOG.md and the 1.0 gate
report). Repository: https://github.com/qompassai/seahawk.
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
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
MCP gateway with runtime security policy, tool-call-level control, and audit of agent actions.
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
Governed app access for AI agents: 1,000+ apps & 12,000+ tools via Code Mode MCP.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to control the Unity Editor through MCP, allowing scene building, runtime scripting, visual QA, and more.5Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to control and query Unreal Engine 4.27.2 editor through MCP, supporting asset creation, level editing, and project inspection via Python remote execution.129 npm35MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI coding agents to work inside a live Unreal Editor for Fortnite session: write and compile Verse, place and wire Creative devices, edit Scene Graph entities, manipulate actors and assets, take screenshots, run playtests, and read editor logs via MCP.MIT
- AlicenseAqualityBmaintenanceEnables AI agents to operate the Unreal Editor via MCP: reading, creating, and editing blueprints at the node level, authoring materials and UMG widgets, auditing projects, and verifying runtime behavior in PIE with read-back checks.341Apache 2.0