Skip to main content
Glama

HeySale — AI Website Salesperson

Server Details

Create and install an AI Website Salesperson for sales, qualification, and lead capture.

If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
Repository
heysale/heysale-mcp
GitHub Stars
0
ChatGPT
–
Claude
–

TDQS

A3.6/5.0

Scored across 6 tools

Disambiguation3/5

Three of the six tools (check_salesperson_status, get_salesperson_installation, verify_salesperson_installation) all answer variants of 'is the script detected on the site?', which forces the agent to parse fine print to pick one. The descriptions do differentiate (readiness vs. snippet retrieval vs. telemetry verification), but the boundaries are blurry enough that misselection is likely.

Naming Consistency4/5

All names use a consistent snake_case verb_noun pattern (check_, configure_, create_, get_, verify_) scoped to the salesperson object, which is highly predictable. The only wrinkle is that check_ and verify_ are near-synonyms used for overlapping detection queries, slightly weakening the verb signal.

Tool Count4/5

Six tools is a tight, well-scoped surface for a create-configure-monitor workflow and each tool maps to a lifecycle step. It leans slightly thin — the three status/detection tools could be consolidated, and there is no listing tool.

Completeness3/5

The create → configure → install → measure lifecycle is covered, but there is no delete/remove operation for a salesperson and no way to list existing salespersons, both of which are natural expectations. Configuration is also limited to name/tagline/goal, leaving no path to update the website URL or other settings.

Available Tools

6 tools
check_salesperson_statusCheck a salesperson's readinessA
Read-onlyIdempotent
Inspect

Find out whether a website salesperson has finished reading the website and is ready to talk to visitors, and whether its script has been detected on the live site. Give it the salesperson_id and the access_token returned when the salesperson was created.

Inputs: salesperson_id (required), api_key, access_token. Returns: domain, status, installed, ownership, +11 more

configure_salespersonChange how a salesperson introduces itselfA
Idempotent
Inspect

Change a salesperson's name, its opening line, or the goal it works towards. While a salesperson is still unclaimed this can be set as part of setting it up. Once the website owner has claimed it, changes must be made by the owner in HeySale — do not ask anyone for an API key.

Inputs: salesperson_id (required), name, api_key, greeting, +1 more. Returns: status, message, success, updated, +11 more

create_website_salespersonCreate a website salespersonA
Idempotent
Inspect

Give any public website an AI salesperson that talks to its visitors, answers questions about the business, and captures leads. Use this when someone wants to add a salesperson, live chat, a sales assistant or a chatbot alternative to a site. Provide the website address; the salesperson reads the site itself. The response always includes an explicit salesperson_id — keep it, because every other HeySale tool needs it — plus the one-line install script, a claim_url to give the website owner, and a private access_token — keep it and pass it to the other salesperson tools; never share it. Calling again for a website that already has a salesperson returns its id and status only. To try HeySale without touching a real website, use website_url https://hey.sale/mcp-test — that creates an isolated, disposable test salesperson on HeySale's own reviewer sandbox.

Inputs: website_url (required), campaign, business_name, integration_source, +1 more. Returns: note, reused, status, success, +13 more

get_salesperson_installationGet the install scriptA
Read-onlyIdempotent
Inspect

Return the exact one-line script to add to a website so its salesperson appears for visitors, plus where to place it and whether HeySale has detected it yet. Give it the salesperson_id and the access_token returned when the salesperson was created.

Inputs: salesperson_id (required), api_key, access_token. Returns: status, ownership, expires_at, environment, +8 more

get_salesperson_resultsSee what the salesperson achievedA
Read-onlyIdempotent
Inspect

Summarise how many visitors talked to the salesperson, how many left their details, and what they asked about most. This is private business data: it is only returned to an authorised caller. Never ask a website owner for an API key — send them to HeySale instead.

Inputs: salesperson_id (required), days, api_key. Returns: note, leads, status, ownership, +16 more

verify_salesperson_installationVerify a salesperson's website installationA
Read-onlyIdempotent
Inspect

Check whether a HeySale salesperson has actually been installed on its website and is reporting back to HeySale. Uses HeySale's own telemetry, so it works with single-page apps, tag managers and deferred script loading — never scrape the website's HTML to answer this. Give it the salesperson_id and the access_token returned when the salesperson was created.

Inputs: salesperson_id (required), api_key, access_token. Returns: domain, status, message, installed, +12 more

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Sales Intelligence · B2B Lead Extraction An MCP (Model Context Protocol) server that gives AI agents structured B2B lead intelligence extracted directly from company websites. Point it at any URL and get back a clean JSON object — company summary, buying signals, inferred needs, and personalised icebreaker lines — ready to drop into your outreach pipeline. Built for agent pipelines. Works with Cl
      1
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.