The firewall for MCP tool calls. Block, audit, replay with evidence bundles.
MCPpedia last refreshed this data
Assay MCP Server is an MCP server that the firewall for MCP tool calls. Block, audit, replay with evidence bundles. Its tool list has not been published yet over stdio, sse and http, requires no API key, and scores 83/100 on MCPpedia's security, maintenance and efficiency rubric.
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"io-github-rul1an-assay": {
"args": [
"-y",
"@modelcontextprotocol/server-filesystem"
],
"command": "npx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Your MCP agent calls read_file, exec, web_search — but should it, and what can you honestly prove about that run afterward?
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
npx -y '@modelcontextprotocol/server-filesystem' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
@modelcontextprotocol/server-filesystem vulnerability allows for path validation bypass via colliding path prefix
Versions of Filesystem prior to 0.6.3 & 2025.7.1 could allow access to unintended files in cases where the prefix matches an allowed directory. Users are advised to upgrade to 2025.7.1 to resolve the issue. Thank you to Elad Beber (Cymulate) for reporting these issues.
>= 0source →@modelcontextprotocol/server-filesystem allows for path validation bypass via prefix matching and symlink handling
Versions of Filesystem prior to 0.6.3 & 2025.7.1 could allow access to unintended files via symlinks within allowed directories. Users are advised to upgrade to 2025.7.1 to resolve. Thank you to Elad Beber (Cymulate) for reporting these issues.
>= 0source →Click any tool to inspect its schema.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in security
Regression testing for MCP servers. Checks capabilities, invokes tools, detects schema drift.
AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.
MCP server for RocketCyber Managed SOC — incidents, alerts, agents, and customer telemetry.
Proof primitive for AI agents on MultiversX. Anchor file hashes on-chain as verifiable proofs.
MCP Security Weekly
Get CVE alerts and security updates for Assay MCP Server and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
The open, recomputable evidence profile for privileged MCP tool actions.
Assay records what a privileged tool call decided, what was observed, and what stays unproven, so a reviewer can replay the claim offline instead of trusting the agent's account of itself. Enforcement is deterministic and fail-closed, and the enforcing proxy is the reference producer rather than the contract itself. Kernel-level (eBPF/LSM) observation on Linux is an optional stronger vantage. CI-native, no backend, bounded by design.
Quickstart · How it works · See it work · MCP example · OWASP MCP Top 10 · Discussions
Agents got real tool access through MCP — and tool poisoning, rug pulls, and confused-deputy OAuth came with it. Most tools scan a server or filter a prompt. Assay sits at the tool-call boundary and does three things, in order.
One golden path: the release-pinned agent journey records the nine driven CLI/MCP steps and their exit/stdout contracts. Its protected-action fixture lives in examples/privileged-action-gate/.
tools/call before it runs, with the precise reason for each allow or deny. On Linux it adds real kernel enforcement — an eBPF/LSM IPv4/TCP connect-egress block and a Landlock TCP-connect port allowlist, both opt-in and fail-closed. A policy it cannot express exactly is refused, never half-applied.verified, self_reported, inferred, absent), and a gate refuses to let a claim exceed what was observed. A tool returning "success" is the provider's assertion, never proof. Assay ships no single safety score and never claims more than it can prove.cargo install assay-cli --version 5.4.0 --locked
mkdir -p /tmp/assay-demo && echo "safe content" > /tmp/assay-demo/safe.txt
assay mcp wrap --policy examples/mcp-quickstart/policy.yaml \
-- npx @modelcontextprotocol/server-filesystem /tmp/assay-demo
✅ ALLOW read_file path=/tmp/assay-demo/safe.txt reason=policy_allow
❌ DENY read_file path=/tmp/outside-demo.txt reason=path_constraint_violation
❌ DENY exec cmd=ls reason=tool_denied
Project manifests are shipped for Claude Code and Cursor; Codex uses the equivalent TOML entry documented in the editor MCP recipe. assay mcp config-path supports Claude and Cursor only. Python SDK: pip install assay-it. CI: GitHub Action. No hosted backend and no API keys for core flows. New to the threat model?