Skip to content
Hear logo

Hear MCP server

Which MCP servers are Hear's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-09

← Back to Hear

Whose server it is
  • Addresshttps://mcp.hear.ai/mcpnot in the official registry: answered when asked

No entry in the official MCP registry names this server. It answered on hear.ai when the Atlas asked at the address servers are usually mounted on, so it is the vendor's own. Clients and catalogues that list servers from the registry do not show it.

When we asked itchecked 2026-10-27
  • Stateanswerschecked 2026-10-27
  • Tools13
  • Server calls itselfhear-ai-platform-sse
  • Server version1.30.0
  • Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 831 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.

Once connected

  • Parameters are untyped or undescribed in 7 of 13 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 7, the first on 2026-10-27
  • INITE MCP score87 of 100answers 86 · definitions 74 · context 100 · connects 100
  • Answered86% of days6 of 7 daily checks
  • Median first answer889 ms
  • Space in an agent's context≈ 1,880 tokensthe definitions of all its tools (13), which an agent carries on every turn
  • Tool definitionsC · 74 of 100
  • Typed results0 of 13 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 7 of 13
  • Not saying whether it only reads or can destroy: 13 of 13

What an agent can do with it

  • not sure · Analyze calls and chats to identify quality issues and coaching opportunities
  • not sure · Monitor compliance across all interactions automatically without manual audits
  • not sure · Detect revenue risks and sales opportunities from customer conversations

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers13 tools · read 2026-10-27
  • list_projects

    List all HearAI contact-center projects this user has access to. Always call this first to get valid project IDs.

  • query_database

    Query the contact-center call database in natural language. Returns counts, aggregations, call lists, statistics, and more. Internally generates a MongoDB aggregation pipeline from your question.

  • db_schema

    Explore what fields and data are available in the database for a project. Use this before query_database to understand available columns.

  • fetch_reports

    List or fetch reports, scheduled insights, and monitor/alert configurations.

  • org_tree

    Get the organizational hierarchy: organizations, teams, users, roles, and agent IDs. Useful for filtering data by team or agent.

  • memory

    Store or retrieve persistent AI memories scoped to a project or user.

  • platform_metrics

    Get KPI metrics for a project: call volume, audio hours processed, and counts of active signals, monitors, and reports. Returns monthly trends and totals for the requested period.

  • signals_overview

    List all configured signals (AI processing columns) for a project. Shows signal names, keys, types, and whether they were created by AI or a user. Use this to understand what data is being extracted from calls.

  • global_overview

    Get a cross-project overview of all accessible projects. Returns call volumes, active signals, monitors, and reports for each project over the last 30 days. Use this for a high-level platform summary.

  • list_tenants

    List all active tenants on the platform (super-admins only). Queries the meta database connection registry. Use this to see which customer tenants are active, their names, and plans.

  • manage_signals

    Create, update, or delete AI processing signals (columns) for a project. Admins and super-admins only for write actions. Actions: list, get, create_signal, update_signal, delete_signal, add_item, update_item, delete_item, toggle_active.

  • manage_alerts

    Create, update, or delete monitor alerts for a project. Admins and super-admins only for write actions. Actions: list, get, create, update, delete, toggle_active.

  • manage_reports

    Create, update, or delete scheduled reports for a project. Admins and super-admins only for write actions. Actions: list, get, create, update, delete, toggle_active.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "hear": {
      "type": "http",
      "url": "https://mcp.hear.ai/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http hear https://mcp.hear.ai/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://mcp.hear.ai/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.