wezterm-agent-mcp
Enables orchestration of multiple AI coding agents (Claude Code, Gemini CLI, etc.) in isolated Wezterm panes, allowing one agent to spawn, monitor, and communicate with others across projects.
Caution. Specific findings reduced this grade. They are listed on the page. 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
multiagentcognition
Source: Glama
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.
MACP_PROJECT_ROOTFallback if WEZ_PROJECT_ROOT not set —ProgramFilesSUDO_USERWEZ_GIT_BRANCHInformational git branch (not enforced) auto-detectedWEZ_PROJECT_ROOTDefault working directory for all panes process.cwd()XDG_CONFIG_HOMETool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
41/41 tools missing one or more hints — wez_status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); wez_list (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); wez_read_tab (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +38 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Destructive tools are labelled
6 tools perform destructive updates without destructiveHint — wez_launch_grid deletes at line 2141 (unlinkSync(join(dir, entry))); wez_launch_agents deletes at line 2141 (unlinkSync(join(dir, entry))); wez_launch_mixed deletes at line 2141 (unlinkSync(join(dir, entry)))
Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.
Descriptions match behaviour
7 tools describe read intent but their handlers mutate — wez_status (line 831: execFileSync(weztermBin(), ['cli', ...args], {); wez_list (line 831: execFileSync(weztermBin(), ['cli', ...args], {); wez_read_tab (line 831: execFileSync(weztermBin(), ['cli', ...args], {)
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool inputs are validated
32/41 tool handlers declare input schemas (78%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tests exist
No test files found
Add tests that exercise each declared tool.
No arbitrary install scripts
Has postinstall/preinstall script — runs arbitrary code on npm install
Remove postinstall/preinstall hooks unless they’re essential.
Tool description accuracy
6 tools have description/behavior mismatches: wez_status: description implies read-only but handler writes/deletes/executes; wez_list: description implies read-only but handler writes/deletes/executes; wez_read_tab: description implies read-only but handler writes/deletes/executes
Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.
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/multiagentcognition/wezterm-agent-mcp)?variant=verified from the 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