# Eclipse Social Core MCP (pypi · eclipse-social-core)

One canonical, hash-bound package behind every Eclipse social adapter. It publishes nothing itself

- Trust score: 68/100 (medium)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- pypi · `eclipse-social-core`: 68/100 (this document), [markdown](https://verifymcp.io/servers/cyan-eclipse-technologies-llc-social-core/eclipse-social-core.md), [page](https://verifymcp.io/servers/cyan-eclipse-technologies-llc-social-core/eclipse-social-core)

## Channel facts

- Registry: `pypi`
- Package: `eclipse-social-core`
- Version: `0.1.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 71/100
  - Repository check failed: the declared repository URL redirects; it must resolve directly.
  - Cryptographically verified build provenance (signed, bound to CYAN-ECLIPSE-TECHNOLOGIES-LLC/eclipse-social-core-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 8 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 56/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1112 tokens (~74/item across 15 items; 15 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "adapter_kill_switch" implies "kill" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Eclipse Social Core MCP server?

Eclipse Social Core MCP runs locally as a PyPI package, launched with uvx eclipse-social-core. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add cyan-eclipse-technologies-llc-social-core -- uvx eclipse-social-core
```

### Cursor

```json
{
  "mcpServers": {
    "cyan-eclipse-technologies-llc-social-core": {
      "command": "uvx",
      "args": [
        "eclipse-social-core"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "cyan-eclipse-technologies-llc-social-core": {
      "command": "uvx",
      "args": [
        "eclipse-social-core"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add cyan-eclipse-technologies-llc-social-core -- uvx eclipse-social-core
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "cyan-eclipse-technologies-llc-social-core": {
      "type": "local",
      "command": [
        "uvx",
        "eclipse-social-core"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add cyan-eclipse-technologies-llc-social-core --command uvx --arg eclipse-social-core
```

### Hermes

```yaml
mcp_servers:
  cyan-eclipse-technologies-llc-social-core:
    command: "uvx"
    args: ["eclipse-social-core"]
```

### Netclaw

```json
{
  "McpServers": {
    "cyan-eclipse-technologies-llc-social-core": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "eclipse-social-core"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add cyan-eclipse-technologies-llc-social-core -t stdio -c uvx -a eclipse-social-core
```

### Other

```json
{
  "mcpServers": {
    "cyan-eclipse-technologies-llc-social-core": {
      "command": "uvx",
      "args": [
        "eclipse-social-core"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-03 (score 68, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-02 (score 53, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-01 (score 68, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-31 (score 53, −15)

- [security regression] Malware scan: pass → unverified

### 2026-10-29 (score 68, +10)

- [security regression] Source repository: pass → fail
- [security improvement] Malware scan: unverified → pass

### 2026-10-27 (score 58)

First indexed and scored.

## MCP tools (15)

### `account_set` (~146 tokens)

Register/update an authorized account: platform, adapter, owner, role, declared capability modes (capability -> mode), and the latest capability probe {status: ok|failed, at, terms_version}. A FAILED probe downgrades effective modes automatically (write modes collapse to prep; reads flagged). Evaluation only — no platform is contacted, no credentials are held.

Input parameters:

- `account_id` (string, required)
- `account_type` (string)
- `adapter` (string)
- `connection_state` (string)
- `modes` (object)
- `owner` (string)
- `platform` (string)
- `probe` (object)
- `role` (string)

### `account_inventory` (~34 tokens)

All registered accounts with declared + effective mode matrices, last probe, and kill-switch state. No credential values exist in this system.

### `content_ingest` (~88 tokens)

Ingest a canonical content object (SS3.1): masters + provenance, copy, claims WITH sources, rights per asset, accessibility assets, disclosure record, intended/prohibited surfaces, schedule. Validates and issues the SHA-256 content hash; re-ingesting changed content bumps the version. Missing rights/claims-sources/alt-text are named blockers.

Input parameters:

- `content` (object, required)

### `content_get` (~29 tokens)

One canonical content record in full, hash + approval state included.

Input parameters:

- `canonical_id` (string, required)

### `adapt_preview` (~114 tokens)

Build one native variant for an adapter profile (aperture_feed, aperture_reel, aperture_story, prism_shorts, zephyr, wire): media geometry, copy under the surface's limit, the surface's working link placement, platform-required disclosure labels, element order — plus the classified adaptation diff. The variant is hash-bound at build.

Input parameters:

- `account_id` (string)
- `adapter` (string, required)
- `canonical_id` (string, required)
- `mode` (string)
- `schedule` (object)

### `adaptation_diff` (~70 tokens)

The classified diff for a built variant (MEDIA_CROP, TEXT_REWRITE, LINK_PLACEMENT, ORDER, DISCLOSURE, METADATA, FORMAT_OMISSION, ...). Substantive changes — numbers, claims, CTA — are flagged, never silent.

Input parameters:

- `variant_id` (string, required)

### `variant_revise` (~68 tokens)

Revise a variant's copy/hashtags/schedule/destination/link/disclosures/order/media. HASH LAW: the hash recomputes; an approval bound to the old hash is invalidated and the variant returns to review.

Input parameters:

- `changes` (object, required)
- `variant_id` (string, required)

### `approval_pack` (~51 tokens)

The review artifact (SS3.2 tool 6): canonical item + every native variant + diffs + destination/account + schedule. This is the object the owner approves.

Input parameters:

- `canonical_id` (string, required)

### `approve_variant` (~43 tokens)

Record the owner's approval of one variant, bound to the exact canonical hash and exact variant hash.

Input parameters:

- `approver` (string, required)
- `variant_id` (string, required)

### `approval_check` (~47 tokens)

Verify a variant's approval is still valid: recompute the hash from current fields and compare with the approved hash. Any post-approval change = invalid.

Input parameters:

- `variant_id` (string, required)

### `policy_check` (~171 tokens)

Engagement policy evaluator — the house playbook as data (SS5). action: like | comment | report_stop | reset. Enforces week-1 caps (15 likes / 5 comments per day) and week-2+ caps (30/10), the 2-likes-per-target cap, no links / no self-promo / no hashtag stuffing / <=1 emoji in comments, no duplicate comments, and stop-signal finality. EVERY check is receipted, ALLOW and DENY alike.

Input parameters:

- `account_id` (string)
- `action` (string, required)
- `adapter` (string)
- `comment_text` (string)
- `counts` (object)
- `owner_reset` (boolean)
- `signal` (string)
- `week` (integer)

### `engagement_log` (~131 tokens)

Append one executed or owner-completed engagement action to the append-only log (timestamp, account, adapter/mode, target, action, full comment text, why, result, cap context, stop state).

Input parameters:

- `account` (string)
- `action` (string, required)
- `adapter` (string)
- `comment_text` (string)
- `mode` (string)
- `result` (string)
- `stop_or_warning` (string)
- `target_account` (string)
- `target_url` (string)
- `ts` (integer)
- `why` (string)

### `engagement_report` (~35 tokens)

Daily-report view over the engagement log: every action, totals vs the week's caps, stop state.

Input parameters:

- `week` (integer)

### `adapter_kill_switch` (~63 tokens)

Independently disable one capability scope: family | adapter | account. Write capabilities freeze first; drafts and receipts remain readable.

Input parameters:

- `account_id` (string)
- `adapter` (string)
- `on` (boolean)
- `scope` (string, required)

### `receipt_list` (~22 tokens)

The append-only, hash-chained receipt ledger, with chain verification.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/cyan-eclipse-technologies-llc-social-core/eclipse-social-core#diagnostics

## Score history

- 2026-11-05: 68
- 2026-11-04: 68
- 2026-11-03: 68
- 2026-11-02: 53
- 2026-11-01: 68
- 2026-10-31: 53
- 2026-10-30: 68
- 2026-10-29: 68
- 2026-10-28: 58
- 2026-10-27: 58

## Common questions

### What is the Eclipse Social Core MCP server?

Eclipse Social Core MCP is listed in the public MCP registry as io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/social-core. One canonical, hash-bound package behind every Eclipse social adapter. It publishes nothing itself. This page covers its PyPI package (eclipse-social-core).

### Is the Eclipse Social Core MCP server safe to use?

Eclipse Social Core MCP scores 68 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Eclipse Social Core MCP server expose?

Eclipse Social Core MCP exposes 15 tools: account_set, account_inventory, content_ingest, content_get, adapt_preview, and 10 more. Their descriptions and schemas cost roughly 1,112 tokens of context every time the server is loaded.

### Is the Eclipse Social Core MCP server still maintained?

Eclipse Social Core MCP is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Eclipse Social Core MCP server under?

Eclipse Social Core MCP declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/eclipse-social-core/
- Socket report: https://socket.dev/pypi/package/eclipse-social-core
- Website: https://eclipsebazaar.com/
- Changelog RSS feed: https://verifymcp.io/servers/cyan-eclipse-technologies-llc-social-core/eclipse-social-core.xml
- Changelog JSON feed: https://verifymcp.io/servers/cyan-eclipse-technologies-llc-social-core/eclipse-social-core.json
- HTML version of this page: https://verifymcp.io/servers/cyan-eclipse-technologies-llc-social-core/eclipse-social-core