About Liliphant
Liliphant is a remote MCP server for company meetings, letting AI assistants query transcripts and trace decisions, commitments, questions, and risks to the words spoken. It also provides meeting filters and tools for accessing Liliphant documentation and APIs.
Key features
- 01Transcribes meetings and extracts content
- 02Filters by text, type, person, tag, or date
- 03Answers meeting questions with quotes
- 04Accesses Liliphant docs and API references
- 05Calls Liliphant API endpoints
Use cases
- 01Find meetings by person or date range
- 02Verify decisions and commitments against quotes
- 03Query open questions and risks from meetings
MCP support
Liliphant is a remote MCP server over Streamable HTTP. AI clients connect after signing in to Liliphant and can read meetings or use its tools.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.liliphant.com/mcpclaude mcp add --transport http com-liliphant-mcp https://mcp.liliphant.com/mcp{"mcpServers":{"com-liliphant-mcp":{"type":"http","url":"https://mcp.liliphant.com/mcp"}}}Open in Cursor{"servers":{"com-liliphant-mcp":{"type":"http","url":"https://mcp.liliphant.com/mcp"}}}Open in VS Code{"mcpServers":{"com-liliphant-mcp":{"type":"http","url":"https://mcp.liliphant.com/mcp"}}}{"mcpServers":{"com-liliphant-mcp":{"serverUrl":"https://mcp.liliphant.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project README
Liliphant MCP
Liliphant joins your company's calls, transcribes them and pulls out decisions, promises, open questions and risks, each linked to the words someone said. This MCP server lets AI assistants read your meetings and answer questions from what people actually said.
It is a remote MCP server (Streamable HTTP) at https://mcp.liliphant.com/mcp. Nothing to install: your AI tool connects to it, and you sign in to Liliphant once in the browser.
Tools
| Tool | What it does |
|---|---|
get_me | Who is signed in and the companies they can open |
list_meetings | Your meetings, newest first; filter by text, type, person, tag or date |
ask_a_question | Answers from your meetings, with quotes |
search_liliphant_docs, get_liliphant_api_docs, quickstart-liliphant | Liliphant docs and API reference |
call_any_read_api_of_liliphant, call_any_api_of_liliphant | Any other Liliphant API endpoint (read, or create/change/delete) |
Connect from Cline
Install it from the Cline MCP Marketplace, or open MCP Servers → Configure MCP Servers and add this to cline_mcp_settings.json:
{
"mcpServers": {
"liliphant": {
"type": "streamableHttp",
"url": "https://mcp.liliphant.com/mcp",
"disabled": false,
"autoApprove": []
}
}
}
Then use the sign-in button next to liliphant in the MCP Servers list and sign in to Liliphant in the browser. Agent-driven install steps are in llms-install.md.
Connect from Claude Code
claude mcp add --transport http liliphant https://mcp.liliphant.com/mcp
then run /mcp and sign in.
MCP Registry
server.json is the listing for the official MCP Registry, as com.liliphant.mcp/mcp. The com.liliphant.mcp name is proven by owning the mcp.liliphant.com domain.
One-time setup: create a signing key and publish its public half on liliphant.com (Git Bash or any shell with OpenSSL):
openssl genpkey -algorithm Ed25519 -out mcp-registry-key.pem
echo "v=MCPv1; k=ed25519; p=$(openssl pkey -in mcp-registry-key.pem -pubout -outform DER | tail -c 32 | base64)"
Add the printed line as a TXT record on liliphant.com. Keep mcp-registry-key.pem private and out of this repo.
Publish (bump version first for any later change):
mcp-publisher login dns --domain mcp.liliphant.com --private-key "$(openssl pkey -in mcp-registry-key.pem -noout -text | grep -A3 'priv:' | tail -n +2 | tr -d ' :\n')"
mcp-publisher publish
Links
- Website: https://liliphant.com
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.