MCP server · Code & DevOps

io.github.viridis-security/injection-detector

By viridis-security Verified namespace

Formally-verified injection/exfiltration detector for AI agents (MCP-02).

Source code AI models & agents

Connect to io.github.viridis-security/injection-detector

Checks passed: 13 / 22

1 failed · 8 not measured

Median response: 330 ms

Median of successful probes over 7 days

30-day uptime: Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools: 2

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Responded

The server completed its last measured handshake. This is an observation, not a guarantee.

Last checked 18 hr ago

Check summary by test group
Test area	Passed	Failed	Unmeasured
ConnectionCan a client connect and discover tools?	5	0	0
Reliability & speedDoes it respond consistently and quickly?	0	0	4
Access & authenticationWhat is required to use this server?	1	0	2
Tool qualityAre the tool definitions usable by an agent?	3	1	0
Publisher identityCan the publisher be traced to its source?	4	0	2

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

Pass
Reachable
Latest probe returned HTTP 200 in 330 ms.
18 hr ago
Pass
Valid handshake
protocolVersion 2025-11-25, serverInfo.name viridis-injection-detector.
18 hr ago
Pass
Lists tools
tools/list returned 2 tools.
18 hr ago
Pass
Current protocol
Negotiated 2025-11-25. The bar is 2025-06-18 or newer.
18 hr ago
Pass
HTTPS
The endpoint URL is https.

Performance

Not measured
Fast (p50)
Median latency 330 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.
Not measured
Consistent (p95)
95th percentile 330 ms over 1 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.
Not measured
Reliable (uptime)
1 of 1 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.
Not measured
Stable tool list
Fewer than two successful probes in 30 days, so tool-list stability is not measured.
18 hr ago

Access

Pass
Open access
tools/list succeeded with no credential, and the record declares none.
18 hr ago
Not measured
Standard auth
Auth is not required, so the OAuth metadata check does not apply.
Not measured
Free tier cited
No publisher quote has been checked.

Tools

Pass
Tools described
Every tool description is at least 20 characters.
18 hr ago
Pass
Valid input schemas
Every inputSchema is a JSON Schema object.
18 hr ago
Pass
Parameters documented
7 of 7 parameters have a description (100%). The bar is 80%.
18 hr ago
Fail
Safety hints
2 tools set neither readOnlyHint nor destructiveHint.
18 hr ago

Publisher

Pass
Verified namespace
Listed in the Official MCP Registry.
Not measured
Website matches publisher
This namespace is not a reverse domain, so the website comparison does not apply.
Pass
Source repo linked
A repository URL is on file.
Pass
Repo owner matches
The GitHub repository owner matches the namespace login.
Pass
Recently updated
Updated 2026-05-30T14:39:37.937428Z, within 180 days.
5 mo ago
Not measured
Open-source licence
The GitHub licence lookup has not returned an OSI result yet.

Start using io.github.viridis-security/injection-detector

Connect to this server

Choose your client, copy the configuration, then enable the server in your client’s MCP settings.

Run this command in your terminal, then restart Claude Code.

Claude Code

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

Capabilities

Tools 2

detect_injection

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, and a recommended action (allow|sanitize|reject|escalate). Backed by Aristotle-verified theorems T-IB-02/T-IB-06/T-IB-01.

Discovered 18 hr ago

detect_trace_tool_policy

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 by T-IB-25/T-IB-29/T-IB-36.

Discovered 18 hr ago

Recent measurements

Probe history

View status

Latest stored probes. Raw probe rows are kept for 14 days.
Checked	Result	Response	Tools
18 hr ago	Connected	330 ms	2

Published by

viridis-security

Publisher of io.github.viridis-security/injection-detector, listed under io.github.viridis-security.

The namespace matches a verified registry identity. Identity verification does not certify the server’s security.

GitHub profile All publisher servers

Server details

Version: 0.1.0
Transport: streamable-http
Authentication: No requirement recorded
Listing source: MCP Registry

io.github.viridis-security/injection-detector

View registry record

For maintainers

Your MCP, in focus.

Share a live health badge with your users and keep this profile connected to your project.

Claim this listing

Add a README badge

Add badge to your README

The image links back to this page. It shows checks passed, or uptime, and the colour follows the latest status. Responses are cached for 5 to 15 minutes.

Markdown

[![MCP Heartbeat](https://mcpheartbeat.com/badge/io.github.viridis-security/injection-detector.svg)](https://mcpheartbeat.com/s/io.github.viridis-security/injection-detector)

HTML

<a href="https://mcpheartbeat.com/s/io.github.viridis-security/injection-detector"><img alt="MCP Heartbeat" src="https://mcpheartbeat.com/badge/io.github.viridis-security/injection-detector.svg"></a>

Uptime markdown

[![MCP Heartbeat uptime](https://mcpheartbeat.com/badge/io.github.viridis-security/injection-detector.svg?kind=uptime)](https://mcpheartbeat.com/s/io.github.viridis-security/injection-detector)

Served from https://mcpheartbeat.com.