Eclipse Constellation MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ECLIPSE_CONSTELLATION_STATE | No | Overrides the path to the state/ledger file (data/state.json by default). | |
| ECLIPSE_CONSTELLATION_POLICY | No | Overrides the path to the policy file (policy.json by default). | |
| ECLIPSE_CONSTELLATION_TARGETS | No | Overrides the path to the targets registry file (targets.json by default). |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| target_listA | List DECLARED targets only (name, kind, address, declared channel, owner agent, desk, declared resources). Undeclared targets are invisible. |
| policy_evaluateA | Evaluate a lifecycle action against policy — evaluation ONLY, nothing executes (v0.1 is observe-only). Returns ALLOW/DENY + reasons + per-check results; every evaluation is receipted, DENYs included. Args: actor {agent, desk}, target, action, params. |
| probe_targetA | Run read-only probes against a DECLARED target over its declared channel. Probes are FIXED templates chosen by name (identity, uptime, disk, memory, services) — there is no free-form command argument, by law. |
| fleet_snapshotA | Probe every declared target and store a receipted fleet snapshot with per-target status and freshness. |
| receipt_listC | List ledger receipts (evaluations incl. DENYs, probes, snapshots) and verify the hash chain. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool targets a distinct resource or operation: listing targets, listing receipts, probing a single target, snapshotting the fleet, and evaluating policy. The only potential overlap is fleet_snapshot vs probe_target, but the descriptions clearly separate aggregate snapshotting from single-target probing.
All names use snake_case, but the ordering is mixed: probe_target is verb_noun, receipt_list/target_list/policy_evaluate are noun_verb, and fleet_snapshot is noun_noun. It remains readable, but there is no single predictable pattern.
Five tools is well-scoped for an observe-only fleet observability and policy-evaluation server. Each tool earns its place, and the set is neither thin nor bloated.
The surface covers the core observe-only workflow: target listing, probing, fleet snapshotting, policy evaluation, and receipt auditing. Minor gaps exist, such as no direct snapshot-detail retrieval or target-declaration operation, but those are arguably outside the stated v0.1 scope.