A
licenseNot graded
qualityB
maintenanceInput/output safety gate for AI agents: detect prompt-injection/jailbreak, leaked secrets/PII, and URL/IP reputation. Deterministic, no LLM.
427 npm
1
MIT
Perspective API Alternative (Toxicity Detection)
Server Details
Toxicity scores (0-1) for text before an agent posts it. Perspective API compatible. No LLM.
Ownership verified
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Uptime
- 55.5% over 23 days
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP
- URL
- Repository
- koyourmoon/perspective-api-alternative-mcp
- GitHub Stars
- 0
- Server Listing
- Perspective API Alternative (Toxicity Detection)
TDQS
A4.2/5.0
Scored across 1 tool
Disambiguation5/5
With only one tool in the set, there is no possibility of misselection or overlap. Its purpose (batch toxicity scoring) is clearly stated and unambiguous.
Naming Consistency5/5
The single tool uses a clean snake_case verb_noun pattern (analyze_toxicity) that would scale predictably if more tools were added. No naming conflicts exist.
Tool Count3/5
A single tool is thin for a server surface, though the narrow scope of a Perspective-API-style scorer makes it defensible. It offers no secondary operations such as listing supported attributes or languages.
Completeness4/5
The one tool covers the core capability well, batching up to 100 texts and returning all Perspective attribute scores. Minor gaps exist (e.g. no multilingual support or attribute-discovery tool), but the primary workflow has no dead ends.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
- First observed
analyze_toxicity
Publisher details
- Operator
- koyourmoon (independent developer) · Publisher source
- Operator website
- https://apify.com/koyourmoon
- Vendor relationship
- Independent
- Trust center
- Not available
- Restrictions
- Requires an Apify account and an Apify API token (Authorization: Bearer <token>). Paid per event: billed per text unit through the Apify account, with Store discounts on higher Apify plans. · Publisher source
Related MCP Connectors
Prompt injection detection API for AI agents. Scan untrusted text before passing it to an LLM.
Toxicity, sentiment, NER, PII detection, and language identification tools
Should I allow this text? Profanity and toxicity checks that are hard to fool, with the evidence.
Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM.
Related MCP Servers
- AlicenseAqualityCmaintenanceLets any AI agent score and simplify its own text before it reaches a human, using Flesch readability metrics and plain-language rewrites entirely on the local machine.2MIT
- AlicenseAqualityCmaintenanceEnables MCP-capable agents to score text for safety, quality, and compliance, returning pass/fail/review verdicts with calibrated confidence in under 500 ms.10207 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to score their outgoing responses against groundedness and prompt-injection risks mid-turn, returning allow, warn, or block verdicts before the response reaches the user.17 npmISC
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd
Glama MCP Gateway
Add one secure layer between your agents and this server.