nushell-mcp
Model Context Protocol server enabling LLMs to use Nushell. Originated as a general shell MCP forked from `capecoma/winterm-mcp`. Narrowed to Nushell to leverage natural language semantics and structured data for human and machine interoperability.
Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
zaynram
Source: github_topic
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
NUSHELL_MCP_BASH_PATH(auto-probe: WSL → Git Bash → bash) Override the bash runner used by nu_exec's bashEnv.NUSHELL_MCP_CONFIG_PATHNUSHELL_MCP_DEBUG_DISPATCHNUSHELL_MCP_MAX_REPLS10 Cap on simultaneous REPL buckets. nu_repl_spawn errors past this.NUSHELL_MCP_NU_PATHfirst nu on PATH Absolute path to the nu executable.NUSHELL_MCP_TIMEOUT_MS30000 Default per-call timeout for nu_exec; the tool's timeoutMs argument overrides it per call.Tool inputs are validated
Only 5/12 tool handlers declare input schemas (42%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
9/12 tool handlers wrap calls in try/catch (75%)
Wrap each tool handler body in try/catch and return a structured error response.
Shell command execution
7 child_process calls — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/zaynram/nushell-mcp)?variant=verified to the badge URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check