Claude MarketplacesSubmit
viridis-security avatar

Injection Detector

viridis-security/mcp-services-sdk

Formally verified protection against prompt injection and data exfiltration for AI agents, backed by Lean 4 proofs. The injection detector analyzes untrusted input and returns a verdict with probability score, bits at risk (via Adversarial Landauer bounds), and recommended action. The canon scanner checks code against a vulnerability database. Both run as hosted API endpoints with a generous free tier (1,000 detections monthly), though you can also grab the open source SDK and integrate via a simple POST. Reach for this when you're building agents that handle user input or execute code and need mathematical guarantees rather than heuristics. The Maxwell service adds adaptive proof of work defenses to make spam expensive for attackers.

tools
2
transport
HTTP
last updated
May 30, 2026
View on GitHub

Install

From registry metadata
$ npx add-mcp https://mcp.viridis-security.com/mcp --name injection-detector

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http injection-detector https://mcp.viridis-security.com/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 2 tools

Verified live against the running server on Nov 6, 2026.

detect_injectionScreen untrusted input for prompt/tool injection, exfiltration, and obfuscation before an agent consumes it. Returns a verdict (clean|suspicious|attack), probability, bits-at-risk (upper bound on adversarial capture per the Adversarial Landauer bound), matched canon patterns,...4 params

Screen untrusted input for prompt/tool injection, exfiltration, and obfuscation before an agent consumes it. Returns a verdict (clean|suspicious|attack), probability, bits-at-risk (upper bound on adversarial capture per the Adversarial Landauer bound), matched canon patterns,...

Parameters* required
agentIdstring
Optional: for MCP-01 envelope cross-check.
certaintystring
Operating point. Default standard.one of quick · standard · premium
contextstring
Optional: the agent's role/system prompt; helps calibrate.
input*string
The untrusted text/data to screen.
detect_trace_tool_policyAnalyze an agent trace for the Gray Swan Wave 16 class: untrusted retrieved/tool output causing a tool call outside the user-declared per-turn allowlist. Returns trace counts, unauthorized tool-call evidence, canon mapping VC-AI-TOOL-0001, and claim-boundary guardrails. Backed...3 params

Analyze an agent trace for the Gray Swan Wave 16 class: untrusted retrieved/tool output causing a tool call outside the user-declared per-turn allowlist. Returns trace counts, unauthorized tool-call evidence, canon mapping VC-AI-TOOL-0001, and claim-boundary guardrails. Backed...

Parameters* required
targetNamestring
Optional display name for the assessed target.
traceobject
Single agent trace with user_prompt, allowed_tools, and events[].
tracesarray
Optional batch of agent traces.

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Readme

Viridis MCP Services

Aristotle-verified attribution-enforcement primitives for AI agents. Production hosted at mcp.viridis-security.com.

pricing docs Aristotle verified

SDK install status, October 6, 2026: the source-declared packages @viridis/mcp-client (npm) and viridis-mcp-client (PyPI) returned package-metadata 404s. Use the source-install instructions. The local import checks need no API key; hosted use still requires separate authorization and a confirmed service contract. Merged source-install PR #8 records that contract/implementation hold. The hosted examples below are not acceptance evidence.

Try in 30 seconds

View the full README on GitHub

Details

Repository
github.com/viridis-security/mcp-services-sdk
Category
Security & Pentesting
Transport
HTTP
Registry
MCP registry, active
Tools verified
Nov 6, 2026

Related Security & Pentesting MCP servers

View all
1weiseer avatarcve-cacheweiseer/cve-cache-mcpRecent CVE + GHSA cache for AI agents auditing dependencies (npm/PyPI/Cargo/Maven/Go).0stars
2shrike-security avatarShrikeshrike-security/shrike-mcpGoverns what AI agents do: tool calls, SQL, commands, files checked against policy before they run.2stars
3promptguardhq avatarPromptGuardpromptguardhq/promptguardScan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client0stars
4egoughnour avatarCode Firewall Mcpegoughnour/code-firewall-mcpStructural similarity-based code filter. Stops malicious code pattern reaching execution tools.0stars
5kloudle avatarKloudle Cloud Security Scannerio.github.kloudle/cloud-security-scannerAWS cloud security scanners for AI agents — S3, IAM, EC2, EKS, RDS, CloudTrail, CloudWatch Logs0stars
6mdfifty50-boop avatarAgent Securitymdfifty50-boop/agent-security-mcpSecurity scanning and threat detection for AI agents0stars