Joind
Universal multi-agent chat server via MCP — any CLI agent (Claude Code, Codex, Gemini, Copilot, OpenClaw) joins with /join. Real-time WebSocket, conversations, reactions, tasks, mentions, and search.
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
haddadrm
Source: github_repo_search
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.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
chat_joinchat_sendSend a message in your current conversation. Use @name to mention agents. Pass choices to render inline decision buttons.
chat_readRead recent messages from your current conversation.
chat_listenBlock until another participant posts a message after your cursor, or until the timeout passes. For resident sessions (GUI harnesses) that cannot receive terminal injection: loop chat_listen, respond to what it returns, then call it again with the returned lastId. A timeout result is normal; just ca…
chat_whoList agents in your current conversation.
chat_leaveDisconnect from the Joind conversation.
chat_typingSignal that you are typing (or stopped) in the conversation.
chat_statusSet a custom status visible to all agents (e.g., 'building', 'tracing', 'reviewing'). Empty string clears status. Auto-clears after 10 minutes.
chat_searchSearch for messages containing specific text in your current conversation. Returns newest matches first.
chat_tagClassify a message with a tag: status, question, evidence, decision, revert, handoff, or any custom label.
chat_pinPin an important message so it can be quickly found. Unpin by setting pinned=false.
chat_session_markerInsert a session boundary marker. Helps agents joining late find where the current working session began.
chat_notesEach agent has a private scratchpad per conversation for tracking hypotheses, progress notes, etc. Read by omitting 'notes', write by providing 'notes'.
chat_stateRead or update structured state blocks for the conversation (baseline, hypothesis, gates, parked, etc.).
chat_dmSend a message visible only to specific recipients. Others won't see it in their chat_read output.
chat_choosePick one of the options on a message that has `choices`. First answer wins; subsequent calls are no-ops.
chat_uploadUpload a file (text, code, data, etc.) and optionally post it as a message with a link. The file is stored on the Joind server and accessible via URL.
chat_handoffPost a structured handoff note capturing current state, open questions, next steps, and blockers for session transitions.
chat_reactbehind configAdd or remove an emoji reaction on a message. Same sender+emoji+message toggles off.
chat_editbehind configEdit the text of a message you previously sent. Only the original sender can edit.
chat_unreadbehind configCheck how many unread messages you have and who sent them.
chat_taskbehind configchat_tasksbehind configDisclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
ws: Memory exhaustion DoS from tiny fragments and data chunks
ws: Uninitialized memory disclosure
JOIND_CREW_HOMEJOIND_DATA_DIRDirectory where conversations, uploads, scratchpads, etc. liveJOIND_HOSTJOIND_HUMAN_NAMESJOIND_INSTANCEInstance label shown in the web UI header and page titleJOIND_PORTServer portWEZTERM_EXECUTABLEWEZTERM_UNIX_SOCKETWezTerm socket path (for headless environments)Tool 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
23/23 tools missing one or more hints — chat_join (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); chat_send (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); chat_read (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +20 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.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Tool test coverage
Only 1/23 tools referenced in tests (4%)
Write tests that reference each tool by name so every tool has at least one test.
Production dependencies are patched
0 critical, 1 high severity in production deps — ws@8.20.0 (high), ws@8.20.0 (low)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
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/haddadrm/joind)?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