Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
pipelock
Agents & frameworksOpen-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.
git clone https://github.com/pipelab-org/pipelock.git -
mcpsec
MCP serversAn AI-driven dynamic protocol fuzzer for the Model Context Protocol (MCP). Prove runtime exploitability by discovering state violations, transport crashes, and application-layer logic flaws (SSRF, LFI) before your AI agents do.
git clone https://github.com/manthanghasadiya/mcpsec.git -
node9-proxy
Agents & frameworksAccess control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on the record.
git clone https://github.com/node9-ai/node9-proxy.git -
mcp-safeguard
MCP serversMCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.
mcp-safeguard@0.3.2 -
mcp-server
MCP serversMCP runtime security. 22µs validation, 97% self-healing. Detects RCE, SSRF, credential hijacking.
correctover-mcp-server@1.2.3 -
HTTP
MCP serversHTTP/REST client with saved collections, env secrets, and SSRF-safe host allowlisting.
@abhishekmcp/http@0.1.0 -
a2a-auditor
MCP serversScans Agent2Agent (A2A) protocol code for webhook SSRF, missing auth, and credential exposure
@guardbee/mcp-a2a-auditor@0.1.1 -
a2a-auditor
MCP serversScans Agent2Agent (A2A) protocol code for webhook SSRF, missing auth, and credential exposure
@guardbee/mcp-a2a-auditor@0.3.1 -
search-mcp
MCP serversWeb search and clean-text page fetch for AI agents, with SSRF protection.
-
search-mcp
MCP serversWeb search and clean-text fetch MCP server (Tavily-powered, SSRF-guarded).
-
Fetch MCP Server
MCP serversHTTP fetch MCP server: SSRF protection, HTML-to-markdown, reader mode, metadata extraction
@yawlabs/fetch-mcp@0.8.8 -
code-guard-mcp
MCP serversSecurity scan for AI-generated code: injection, SSRF, secrets, weak crypto, unsafe deserialization.
@mlawsonking/code-guard-mcp@1.3.0 -
Web Page Fetcher
MCP serversFetch web pages with SSRF protection. Returns clean, readable markdown from any URL.
https://github.com/paimonchan/paimon-mcp-fetch/releases/download/v0.1.2/paimon-mcp-fetch-0.1.2-windows-amd64.zip -
MCP Shield
MCP serversSecurity scanner for MCP servers. SSRF, path traversal, injection, auth, secrets. Grade A-F.
@sophiacave/mcp-shield@1.0.7 -
mcp-web-research
MCP serversWeb search (Brave) and SSRF-safe page fetching, extraction and comparison for agents
@opafex/mcp-web-research@0.1.0 -
corsproxy.dev
MCP serversCall third-party APIs from agents without leaking secrets. SSRF blocked, per-key quotas.
-
agent-runtime-guard
MCP serversAgent 运行时全栈拦截: allow/deny tool calls, Ed25519 receipts, blocks RCE, theft, SSRF, injection. stdio.
agent-runtime-guard@1.0.0 -
safe-fetch
MCP serversMCP server for fetching URLs, safe against SSRF, DNS rebinding, and redirect-to-internal attacks.
safe-fetch-mcp-server@0.6.1 -
Gopher & Gemini MCP Server
MCP serversBrowse Gopher and Gemini resources safely: SSRF protection, TLS/TOFU, structured JSON output.
gopher-mcp@0.10.2 -
Cluefinch MCP
MCP serversLocal-first web research for AI agents with SearXNG search and SSRF-safe page retrieval.
cluefinch@0.1.4 -
mcp-openapi
MCP serversTurn any OpenAPI/Swagger spec into MCP tools — each operation an SSRF-guarded tool.
@infoinlet/mcp-openapi@0.1.1 -
web-retrieval-mcp
MCP serversMCP web search + tiered web fetch for AI agents (Exa, Firecrawl), SSRF-guarded, cross-platform.
web-retrieval-mcp@0.1.2 -
meok-mcp-injection-scan-mcp
MCP serversMCP injection / prompt-poisoning / SSRF scanner. 30+ canonical rules covering the April 2026
meok-mcp-injection-scan-mcp@1.0.14 -
AIMarket MCP Gateway
MCP serversStdio + HTTP MCP gateway: SSRF-hardened web_fetch, web_search, metis_verify, market_search.
aimarket-mcp@0.6.4
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.