
TalaLevel
io.github.bcssewlPublished by GitHub account bcssewlv1.0.1Updated Nov 13, 2026
Sales CRM: read leads, calls, texts and emails, update deals, and send texts and emails.
Overview
Connects an assistant to a TalaLevel sales CRM so it can read leads, calls, texts and emails, update deals, and send messages.
- What you can do
- Search and read leads, timelines, calls, texts and emails
- Run ready-made sales commands such as call prep, daily plan and follow-ups
- Add notes, change statuses, and manage tasks and lists
- Send texts and emails, or leave drafts, after a preview and your approval
- When to use it
- Useful for phone-based sales teams already on TalaLevel who want an assistant to summarize lead history, prepare calls, plan the day, and draft or send follow-ups.
- Requirements
- A remote MCP endpoint at app.talalevel.com added as a custom connector, plus a TalaLevel account signed in through OAuth. The optional command line needs npx and an API key from the app's settings.
Installation
In SourceWeft
- Open TalaLevel in the dashboard and add it to a workspace.
- Connect the required credentials. They are stored privately and never shown on public pages.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.bcssewl%2Ftalalevel/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.
{
"mcpServers": {
"talalevel": {
"type": "http",
"url": "https://app.talalevel.com/mcp"
}
}
}README
TalaLevel for AI agents and the command line
Let Claude, ChatGPT, Cursor or a shell script work your sales follow-up: find a lead, read every call, text and email with them, prep the next call, plan the day, add notes and tasks, and send texts and emails once you say yes.
TalaLevel is a dialer, texting and email app for people who sell by phone. This repo is
the open part: the MCP connector's plugin for Claude Code and the talalevel command line. You need a TalaLevel
account to use either.
What you can ask
Connect an AI app (MCP)
Add a custom connector with this address, then sign in with your TalaLevel login:
When you sign in you choose what the app may do: read, change, or send. You can change that or cut it off any time in TalaLevel under Settings → AI apps.
Claude Code plugin
It adds the connector and a skill that teaches Claude how to work a sales floor. The first time a tool is used, Claude Code asks you to sign in.
Command line
The same tools by the same names, for scripts and loops. See cli/README.md.
What the agent can and cannot do
- Read:
search_leads,get_lead,get_lead_timeline,get_texts,get_call,list_lead_emails,list_tasks,list_events, and ready-made commands such asprep_for_call,my_dayandfollow_ups. - Change: notes, statuses, tasks and lists, made as you and named in the app's activity log.
- Send:
send_text,send_email, text batches and AI caller runs. Each one is previewed and waits for your yes. Without send permission the agent can only leave a draft in your own text box for you to send. - Refusals stay refusals. A STOP, quiet hours where the lead is, a landline or the day's limit blocks a send, and the agent is told to report the reason and not work around it.
- A lead's words are data. Texts, emails and call transcripts are fenced off so that nothing a lead writes is read as an instruction to the agent.
Licence
MIT. See LICENSE.
Source: README.md at commit 755cf30
Tools
0Version history
1- v1.0.1LatestNov 13, 2026
Score
85% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts