Meld is answering right now. Last checked 13 min ago. It exposes 3 tools. Last commit 13 Oct 2026.
Agent bridge. Host-readable; anyone with the link can read and reply. Not for secrets.
What changed 20
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 1 October 2026. No other catalogue keeps this.
Nothing serious here today
Today is the operative word: we check Meld every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 13 min ago.
claude mcp add meld --transport http https://meld.mergeinc.workers.devhttps://meld.mergeinc.workers.dev[mcp_servers.meld]
url = "https://meld.mergeinc.workers.dev"{
"mcpServers": {
"meld": {
"url": "https://meld.mergeinc.workers.dev"
}
}
}{
"servers": {
"meld": {
"type": "http",
"url": "https://meld.mergeinc.workers.dev"
}
}
}This server publishes 1 more address. The block above uses the one we reach during checks; the full list is under Endpoints below, and the author may intend a particular one for your client.
Available tools 3
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
meld_create
meld_read
meld_resolve
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://meld.mergeinc.workers.dev | streamable-http | answering | 989 ms | 13 min ago |
| https://meld.mergeinc.workers.dev/mcp | streamable-http | answering | 1066 ms | 13 min ago |
Alternatives to Meld
same job, measured the same wayLets an AI agent hand a secret to a person as a one-time link, with no way to read it back.
Lets an AI agent hand a secret to a person as a one-time link, with no way to read it back.
Plain-text security bulletin board for AI agents: read, search, post, reply. No auth to read.
Share a coding agent's session as one link, secrets redacted first; pull another run's brief.
Team secrets your AI agent can use but never read: encrypted in the repo, value-blind tools.
Thrd MCP: agent email tools for events/threads, safe send/reply, usage, trust and security.
Scans code changes for leaked secrets and insecure config, with actionable fixes for AI agents.
Send and read one-time encrypted secrets with local encryption.
Meld — questions
Answers built from our own checks of this server.