Agent Workspace MCP
MCP serverRun an agent's code and shell commands in a locked-down Docker workspace
Runs locally- 6 tools
- Open source
- Developer tools
Run an agent's code and shell commands in a locked-down Docker workspace
Runs locallyOffline security checks for code, dependencies and AI agent setup with six read-only tools
Runs locally
Hand coding tasks to sandboxed workers and verify each change before it is committed
Runs locally
Read-only network config checks: drift, CIS/PCI, 802.1X, certs and change risk
Runs locally
CVSS scoring, IOC extraction, email header triage and KEV lookup for analysts
Runs locally
Let an agent pay on NEAR through a vault whose rules a smart contract enforces
Runs locallyFind which CI security checks are missing or cannot fail the build in a repository
Runs locallyMap which functions reach network, files, database or subprocess, then gate risky edits
Runs locallyRead-only MCP server that shows which git name, email and SSH key a repo will use
Runs locallyOperate Proxmox through an AI agent with planned changes, receipts and undo
Runs locallyFind end-of-life runtimes, packages and Actions in a repo, with file, line and source
Runs locallyApproval gateway that keeps AI assistants from reading or changing your data unchecked
Runs locallyFree MCP server that checks lockfiles, Node.js and PHP versions and Dockerfiles for flaws
Not checked yet
Self-hosted fleet of persistent, logged-in stealth Chrome sessions for AI agents
Runs locallyMac key vault where agents get scoped, expiring tokens and never the API keys
Runs locallyRegistry, scoped permissions and one-step recall for AI agents in health systems
Not checked yet
Scan prompts, tool definitions and model output for injection, and guard tool calls
Runs locallyPassive-by-default OSINT lookups for AI agents: DNS, WHOIS, IP, breaches, Shodan and more
Runs locallyLocal security scanner that checks AI-written code and drives a scan, fix, rescan loop
Runs locallyPersistent sandbox for coding agents: run commands, edit files, manage Git and sessions
Not checked yetOpen-source MCP gate that signs an allow, deny or hold before each agent tool call
Not checked yetRead-only CVE triage that explains each verdict from KEV, EPSS and exploit data
Runs locallyTelegram MCP server with a separate key per AI client, scoped to chosen chats
Runs locallyCryptographic identity, delegation and receipts for AI agents, with 154 MCP tools
Not checked yetBlocks destructive SQL before it reaches your PostgreSQL or MySQL database
Runs locallySigned, sealed handoffs between AI agents, with trust decided by the receiver
Runs locallyGive an AI agent its own DID: prove identity offline, verify bundles, pay and message
Not checked yetMCP server and CLI giving coding agents version-matched docs and a dependency check
Runs locallyRead-only operator view of Vongola, a Rust TLS reverse proxy built on Pingora
Runs locallyRust reverse-engineering MCP server that returns evidence-backed findings on binaries
Runs locally