Hosted at [compound.mcp.junct.dev/mcp](https://compound.mcp.junct.dev/mcp). Free to use. No auth. No API key required.
Compound MCP MCP server exists for a simple reason — assistants are far more useful when they can act on Compound MCP directly instead of describing what you should do. Hosted at compound.mcp.junct.dev/mcp. Free to use. No auth. No API key required.
This MCP server is deterministically generated from the Compound API specification. Every tool maps 1:1 to a real API endpoint — no hallucinated endpoints, no phantom tools.
Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
Once Compound MCP is connected, these are the calls the assistant has available:
Protocol — ** CompoundEndpoint — ** https://compound.mcp.junct.dev/mcpTransport — ** Streamable HTTPAuth — ** None requiredDocumentation — ** compound.mcp.junct.dev/llms.txtAmong the knowledge and memory options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Compound MCP's toolset — Protocol, Endpoint, Transport and 2 more — is a fair guide to whether it matches your workflow. It is maintained by junct-bot; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| Protocol | ** Compound |
| Endpoint | ** https://compound.mcp.junct.dev/mcp |
| Transport | ** Streamable HTTP |
| Auth | ** None required |
| Documentation | ** [compound.mcp.junct.dev/llms.txt](https://compound.mcp.junct.dev/llms.txt) |
{
"mcpServers": {
"compound": {
"url": "https://compound.mcp.junct.dev/mcp",
"transport": "streamable-http"
}
}
}Configuration as documented by the project. Restart the client after saving.
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.