mcpField
E
Eclipse Sunset

Eclipse Sunset

Local
eclipsebazaar.comDeveloper Tools0Updated today

About Eclipse Sunset

Eclipse Sunset is a local MCP server that checks tool and version changes across witnessed registry snapshots. It gives agents evidence-backed sunset findings and migration diffs from before-and-after schemas.

Key features

  1. 01Ingest and hash-chain snapshots
  2. 02Detect removals and deprecations
  3. 03Identify version and schema changes
  4. 04Generate config-specific migration diffs
  5. 05Verify claims and chain integrity

Use cases

  1. 01Check whether a tool was removed or deprecated
  2. 02Find schema changes affecting an agent config
  3. 03Verify a sunset claim against snapshot history

MCP support

Exposes five tools to MCP clients for snapshot ingestion, sunset detection, migration diffs, claim verification, and chain checks. It processes local snapshot JSON files and does not crawl live registries.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Eclipse Sunset

MCP deprecation radar — detects deprecated/removed tools and versions from witnessed registry snapshots and generates a migration diff for an agent's config.

Scope label: LOCAL / fixture. v0.1 ingests local registry snapshot JSON files only. It does not crawl live registries. Live crawling is a later phase.

Status: v0.1.1 — CERTIFIED (local, fixture) (Verity re-bench, 2026-10-26: probe 5 chain-attack suite 4/4 + strict extras 9/9, full prior suite 44/44; D1 closed). Spec: SPEC.md.

Novel mechanism

Sunset notices are witnessed against registry history, so a "deprecated" claim is provable — and the migration diff is generated from the witnessed before/after schemas, not scraped docs.

Each ingested snapshot is SHA-256 hashed over its canonical JSON and hash-chained in ingest order (chain_hash = sha256(prev_hash + snapshot_hash)). Findings cite both snapshot hashes of the witnessed pair. A claim with no witnessed pair behind it returns UNPROVEN.

Tools (exactly 5)

ToolWhat it does
ingest_snapshotValidate a snapshot (server_id, version, tools[] with name/inputSchema/deprecated), hash it, chain-append it; returns snapshot id + chain position.
detect_sunsetsBetween two witnessed snapshots of the same server: tools removed, tools newly deprecated, version changes, schema-breaking changes — each finding cites both snapshot hashes.
migration_diffGiven a server + an agent config listing tools used, produce the diff: which used tools are sunset in the newer witnessed snapshot and what changed in their schemas.
verify_sunset_claimClaim "tool X deprecated/removed" → PROVEN only if a witnessed snapshot pair supports it, else UNPROVEN.
chain_statusVerify hash-chain integrity (recomputes every hash + link; tamper → valid: false).

Fixtures

fixtures/weather-v1.json and fixtures/weather-v2.json: the same fixture server at v1.0.0 / v2.0.0 — one tool removed (legacy_lookup), one deprecated (get_alerts), one schema-breaking change (get_forecast gains required units), one unchanged (convert_units). fixtures/agent-config.json is a sample agent config for migration_diff.

Pricing

FREE + funnel role — free radar feeds paid listing-hygiene and re-bench work. No payment anything in this server.

Run

python3 server.py            # MCP over stdio JSON-RPC
python3 -m unittest discover -s tests -v

State (the witnessed chain ledger) lives in data/ or the directory named by SUNSET_DATA_DIR.

Python 3, standard library only.

MIT License · Copyright © 2026 Cyan Eclipse Technologies LLC · cetech.ai

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.