The Agent Forge
MCP serverCheck MCP servers, skills and packages for advisories before your agent installs them
Not checked yet- 6 tools
- Remote
- Free
- Security
Check MCP servers, skills and packages for advisories before your agent installs them
Not checked yet
Self-hosted fleet of persistent, logged-in stealth Chrome sessions for AI agents
Runs locallyGrades any public GitHub repo A to F for safety, in plain English, before you install it
Not checked yetLet your coding agent publish a card, find matching agents and negotiate behind a firewall
Not checked yet
Scan prompts, tool definitions and model output for injection, and guard tool calls
Runs locallyFact-check LLM output claim by claim and gate risky agent actions with a safety layer
Not checked yetReview and block risky AI agent actions, installs and MCP calls on your machine
Runs locallyEgress screening and outbreak telemetry against self-replicating prompt injections
Not checked yetCheck artifacts and action receipts from AI agents for empty content and tampering
Not checked yetSigned, sealed handoffs between AI agents, with trust decided by the receiver
Runs locallyReal email inboxes for AI agents, with a trust report on every message
Not checked yetScan MCP configs for leaked secrets and poisoned tools, and review AI-written code
Not checked yetEmail MCP server for Gmail, Outlook and IMAP that fences messages against prompt injection
Runs locallyRule-based scans for prompt injection, poisoned MCP tools and unsafe x402 endpoints
Not checked yetLocal file inspector and guarded editor that flags hidden content and text aimed at AI
Runs locallyPay-per-call prompt-injection scanner that cleans pages before an agent reads them
Not checked yetScans GitHub repos and shell commands for malware tricks before an agent runs them
Not checked yetSecrets manager MCP server that runs commands with API keys the model never sees
Runs locally
Scans an MCP server for open access and overreaching tools before an agent connects
Not checked yetScreen untrusted text for prompt injection and jailbreaks before it reaches your LLM
Not checked yetRead-only scanner that checks remote MCP servers for tool poisoning and silent changes
Not checked yetTurns web pages and PDFs into clean Markdown and strips hidden prompt-injection text
Not checked yetFetch public web pages as numbered, quotable paragraphs with integrity hashes
Not checked yet
Checks whether a page may be used, then reads it as Markdown or JSON for agents
Not checked yetAuthorization proxy that needs a rule check and AI judges to approve each tool call
Runs locallyChecks a transaction, typed data or text before an agent wallet signs, $0.01 a check
Not checked yetPay-per-call web reading, search, fact-checks and token screening for agents, in USDC
Runs locallyThreat-intelligence verdicts on a URL, domain or IP before a coding agent connects
Not checked yetTurn URLs, PDFs and DOCX files into compact Markdown, with prompt-injection scanning
Not checked yetScore AI agent runs for quality, PII leaks, prompt injection and cost, on your own machine
Runs locally