Unified AI System MCP Gateway
OCI · GHCR.IO/HAPPY520AI/UNIFIED-AI-SYSTEM/MCP-SERVER:0.8.0
Self-hosted MCP gateway for Codex, Cursor, and Cline with provider-free prompt enhancement.
Available components
Last scanned (21 hours ago)
Scores higher than 75% of OCI servers
Category AI and Machine Learning
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. How we score → Why this is hard to score →
Supply Chain Security0
- No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
- Known CVEs could not be checked: this image's dependency list comes from an SBOM its publisher attached, which nothing verifies, so we will not report it as a clean result. View diagnostics → Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: this image's dependency list comes from an SBOM its publisher attached. It names packages and versions but not whether each is deprecated, still maintained or linked to its source, so there is nothing we can fairly grade.Unverified
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 21 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability78
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 884 tokens (~58/item across 15 items; 15 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management63
- Stability observed for 19 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety88
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 1 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "gateway_chat" implies "send" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Partial
- An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
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.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 17 Oct 26 +40
- Injection markers: unverified → pass ▲ security
- MCP protocol: unverified → pass ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- Stability: unverified → 0.63 ▲ functional
- 15 Oct 26 −31
- Tool safety: pass → unverified ▼ security
- Stability: Stability not yet verified: this package installed, but its server did not start, so we have no schema to compare. security
- Tool coverage: 100 → unverified ▼ functional
- Capabilities: pass → unverified ▼ functional
- 28 Sept 26 +31
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- First check of Tool coverage: 100 functional
- First check of Destructive annotations: 50 functional
- First check of Schema quality: excellent functional
- First check of Schema quality: fail functional
- First check of Schema quality: pass functional
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Sept 26 10
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 17 Oct 2026 · Analysed oci/ghcr.io/happy520ai/unified-ai-system/mcp-server:0.8.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | oci |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 21 ungraded findings
From the publisher's SBOM, not graded. These advisories match packages listed in the SBOM the publisher attached to this image. A publisher naming a vulnerable package in their own image is credible, so we show them. Nothing verifies that SBOM, though, so the Known CVEs signal does not grade the image from it.
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-6qxp-vccf-f47h | CVE-2026-104850 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N | yes |
| GHSA-jfc7-64v2-mr8c | CVE-2026-48758 | medium | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:L | yes |
| GHSA-3jxr-9vmj-r5cp | CVE-2026-13149 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L | yes |
| GHSA-6j4f-fj2g-mc7p | CVE-2026-102276 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-f886-m6hf-6m8v | CVE-2026-33750 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H | yes |
| GHSA-mh99-v99m-4gvg | CVE-2026-14257 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-q2hr-2g5m-vwhr | CVE-2026-102277 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L | yes |
| GHSA-qhr7-859c-m2p7 | CVE-2026-102278 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-rgw5-rvv9-x895 | CVE-2026-69152 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-hxh3-vqpv-xpqv | CVE-2026-93981 | medium | CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:L/I:L/A:N | yes |
| GHSA-ch52-4w7c-c8xp | CVE-2026-93748 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N | no |
| GHSA-h3mg-xc3c-68pw | CVE-2026-101911 | medium | yes | |
| GHSA-j6r3-76f7-8jcv | CVE-2026-101912 | medium | yes | |
| GHSA-mwp4-54f8-5fhr | CVE-2026-69192 | high | yes | |
| GHSA-rpw4-54j3-4h4q | CVE-2026-101913 | medium | yes | |
| GHSA-v2v4-37r5-5v8g | CVE-2026-42338 | medium | yes | |
| GHSA-w4pp-8pjf-rmxw | CVE-2026-9496 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-3v7f-55p6-f55p | CVE-2026-33672 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N | yes |
| GHSA-c2c7-rcm5-vvqj | CVE-2026-33671 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-rj75-hqrm-r3gf | CVE-2026-104844 | medium | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
| GHSA-w9m9-85wc-3x92 | CVE-2026-9358 | medium | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:L | yes |
Background: What a vulnerability scan can and cannot prove →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
agent_governance_describe Describe a governed Agent ~52
Describe one governed Agent only when it is visible to the Gateway-authenticated tenant. Cross-tenant and missing identifiers remain indistinguishable.
| Name | Type | Req | Description |
|---|---|---|---|
| agentId | string | yes | Server-issued governed Agent identifier |
No output schema declared.
No examples provided.
agent_governance_list List governed Agents ~33
List only the governed Agents visible to the Gateway-authenticated tenant. The tool accepts no tenant or owner override.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
agent_governance_status Agent Governance status ~40
Inspect Agent Governance status through the authenticated Gateway identity. The tool accepts no tenant override and fails closed when that identity is not authorized for platform status.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
gateway_chat Fake-provider chat ~37
Send one chat request only when the gateway proves that real providers are disabled.
| Name | Type | Req | Description |
|---|---|---|---|
| prompt | string | yes | Prompt for the deterministic local fake provider |
No output schema declared.
No examples provided.
gateway_health Gateway health ~22
Inspect gateway health, provider mode, and the real-provider safety flag.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
gateway_prompt_enhance Natural-language prompt enhancement ~95
Turn a plain-language request into a structured prompt locally without provider credentials or provider calls.
| Name | Type | Req | Description |
|---|---|---|---|
| input | string | yes | The natural-language request to preserve and structure |
| language | string | – | Output language; auto follows the input language |
| profile | string | – | Optional task profile; auto detects a profile from the request |
| target | string | – | Execution target; agent adds a plan-verify-report execution protocol |
No output schema declared.
No examples provided.
gateway_prompt_enhance_llm LLM-enhanced prompt enhancement ~122
Enhance a prompt using LLM semantic rewriting when a provider is available. Falls back to the deterministic local engine when no provider is configured.
| Name | Type | Req | Description |
|---|---|---|---|
| input | string | yes | The natural-language request to enhance |
| language | string | – | Output language |
| modelId | string | – | Optional model ID for LLM enhancement |
| profile | string | – | Optional task profile hint |
| providerId | string | – | Optional provider ID for LLM enhancement |
| target | string | – | Execution target; agent adds a plan-verify-report execution protocol |
No output schema declared.
No examples provided.
gateway_readiness Gateway readiness ~21
Inspect first-run readiness for chat and the local gateway runtime.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
knowledge_readiness Knowledge readiness ~20
Inspect the gateway knowledge infrastructure without loading or changing data.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
knowledge_retrieve Knowledge retrieve ~78
Search the local knowledge base by keyword. Returns ranked chunks with citations. Does not call any provider.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | Search query for keyword-based retrieval |
| sourceIds | array | – | Optional filter to specific knowledge source IDs |
| topK | integer | – | Number of results to return (1-5, default 3) |
No output schema declared.
No examples provided.
workflow_actions Workflow actions ~17
List workflow action definitions without invoking any action.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
workflow_health Workflow health ~18
Inspect the governed workflow subsystem without starting a workflow.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
workflow_run Workflow run ~118
Execute the 3-step local workflow: retrieve knowledge, compose a Markdown report, and write a controlled artifact. Does not call any provider.
| Name | Type | Req | Description |
|---|---|---|---|
| agentId | string | – | Required when the Gateway has Agent Governance enabled |
| artifactName | string | – | Optional filename for the output artifact (without path) |
| goal | string | yes | The workflow goal or objective |
| query | string | – | Optional retrieval query; defaults to the goal |
| topK | integer | – | Number of knowledge chunks to retrieve (1-5, default 3) |
No output schema declared.
No examples provided.
workforce_agents Workforce agents ~18
List configured workforce agent descriptors without dispatching them.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
workforce_health Workforce health ~18
Inspect the workforce subsystem without planning or executing work.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
How do I install the Unified AI System MCP Gateway server?
Unified AI System MCP Gateway runs locally as a container image, launched with docker run --rm -i ghcr.io/happy520ai/unified-ai-system/mcp-server:0.8.0. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
oci · ghcr.io/happy520ai/unified-ai-system/mcp-server:0.8.0
claude mcp add happy520ai-unified-ai-system -- docker run --rm -i ghcr.io/happy520ai/unified-ai-system/mcp-server:0.8.0
What is the Unified AI System MCP Gateway server?
Unified AI System MCP Gateway is listed in the public MCP registry as io.github.happy520ai/unified-ai-system. Self-hosted MCP gateway for Codex, Cursor, and Cline with provider-free prompt enhancement. This page covers its container image (ghcr.io/happy520ai/unified-ai-system/mcp-server:0.8.0).
Is the Unified AI System MCP Gateway server safe to use?
Unified AI System MCP Gateway scores 50 out of 100 on VerifyMCP. The SBOM its publisher attached lists packages with 21 known advisories as of 17 October 2026. We do not grade that SBOM, as nothing verifies it. 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 Unified AI System MCP Gateway server expose?
Unified AI System MCP Gateway exposes 15 tools: gateway_health, gateway_readiness, agent_governance_status, agent_governance_list, knowledge_readiness, and 10 more. Their descriptions and schemas cost roughly 709 tokens of context every time the server is loaded.
Is the Unified AI System MCP Gateway server still maintained?
Unified AI System MCP Gateway is still listed as active in the MCP registry. We last reached this channel on 17 October 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 Unified AI System MCP Gateway server under?
Unified AI System MCP Gateway declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.