Koskamo

Atlas Primer MCP

Atlas Primer MCP enables AI agents to create real-time voice roleplay simulations for enterprise performance training. It allows users to generate scenarios for practicing high-stakes conversations, such as sales objections or difficult feedback, by defining parameters like character, conflict, and success criteria.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Atlas Primer MCP logo, by Atlas PrimerCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-06Published by Atlas Primer
You need:No API keys are required for the calling agent.
MCP endpoint (Streamable HTTP)
https://roleplay.atlasprimer.com/mcp
Vendor documentation

What its tools do

1 tool, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Read-only (1)

1 of 1 have a description · 1 of 1 declare behavior hints · 1 of 1 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Warning Advertises resources/templates/list but does not implement it
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Generate real-time voice simulations for sales training
  • Practice difficult employee performance feedback conversations
  • Simulate customer escalation handling scenarios
  • Conduct executive leadership alignment roleplays

Source and maintenance

Community listingRegistry 1.0.2
mcp-registry: io.github.AtlasPrimer/mcp-server@1.0.2Project website

Protocol and capabilities

Server
@atlasprimer/mcp-server 1.0.0
MCP protocol negotiated in check
2025-11-25
Tools
1 advertised
Resources
1 advertised
Resource templates
Not advertised
Prompts
1 advertised
Server-advertised capabilities
{
  "tools": {},
  "prompts": {},
  "resources": {}
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Use the `create_roleplay_simulation` tool whenever the user wants to practice, rehearse, or prepare for a high-stakes human conversation (such as enterprise sales objections, difficult performance reviews, executive negotiations, customer de-escalations, or regulatory compliance discussions). Formulate a 1-paragraph scenario prompt defining the learner role, counterpart identity and gender, 3 to 4 behavioral resistance traits, the core conflict, and measurable success criteria, then return the generated clickable simulation URL to the user.

Tools

1 advertised

create_roleplay_simulation — Create Voice Roleplay Simulation
Advertised by the server during the last successful anonymous check.
Advertised read-only

Creates a personalized real-time AI voice roleplay simulation on Atlas Primer from a natural-language scenario description. Returns a direct, clickable simulation URL requiring no API keys or pre-registration.

create_roleplay_simulation input schema
{
  "type": "object",
  "required": [
    "prompt"
  ],
  "properties": {
    "prompt": {
      "type": "string",
      "description": "Full 1-paragraph scenario description defining who the user is, who the counterpart is, the core conflict or disagreement, and the stakes."
    },
    "language": {
      "type": "string",
      "description": "ISO-639-1 language code such as \"en\", \"is\", \"es\", or \"ja\" (default: \"en\")."
    },
    "user_role": {
      "type": "string",
      "description": "Learner role and perspective (e.g., \"Senior Account Executive\")."
    },
    "character_name": {
      "type": "string",
      "description": "Counterpart name and title (e.g., \"Elena Rostova, VP of Procurement\")."
    },
    "character_role": {
      "type": "string",
      "description": "Counterpart functional role or authority level."
    },
    "character_gender": {
      "enum": [
        "male",
        "female"
      ],
      "type": "string",
      "description": "Speech synthesis voice gender (\"male\" or \"female\")."
    },
    "failure_criteria": {
      "type": "string",
      "description": "Single sentence defining what triggers conversation failure."
    },
    "success_criteria": {
      "type": "string",
      "description": "Single unambiguous sentence defining measurable conversation success."
    },
    "challenge_keywords": {
      "type": "string",
      "description": "3 to 4 comma-separated behavioral resistance traits (e.g., \"skeptical, defensive, budget-constrained\")."
    },
    "max_duration_minutes": {
      "type": "number",
      "description": "Maximum duration in minutes between 3 and 30 (default: 10)."
    }
  }
}
create_roleplay_simulation output schema
{
  "type": "object",
  "required": [
    "url",
    "query_url",
    "encoded_token",
    "payload"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "Primary clickable simulation URL using Base64URL fragment (#d=...)."
    },
    "payload": {
      "type": "object",
      "required": [
        "prompt"
      ],
      "properties": {
        "prompt": {
          "type": "string"
        },
        "source": {
          "type": "string"
        },
        "language": {
          "type": "string"
        },
        "user_role": {
          "type": "string"
        },
        "character_name": {
          "type": "string"
        },
        "character_role": {
          "type": "string"
        },
        "character_gender": {
          "enum": [
            "male",
            "female"
          ],
          "type": "string"
        },
        "failure_criteria": {
          "type": "string"
        },
        "success_criteria": {
          "type": "string"
        },
        "challenge_keywords": {
          "type": "string"
        },
        "max_duration_minutes": {
          "type": "number"
        }
      },
      "description": "Sanitized simulation payload parameters."
    },
    "query_url": {
      "type": "string",
      "description": "Fallback clickable simulation URL using plain query parameters (?prompt=...)."
    },
    "encoded_token": {
      "type": "string",
      "description": "Base64URL-encoded JSON scenario token."
    }
  }
}
create_roleplay_simulation annotations
{
  "title": "Create Voice Roleplay Simulation",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

1 advertised

practice_conversation — Practice a High-Stakes Conversation

Advertised by the server during the last successful anonymous check.

Design and launch a customized real-time voice roleplay simulation on Atlas Primer for any upcoming meeting, negotiation, sales objection, or difficult conversation.

topic
The core topic, conflict, or upcoming meeting to practice. (required)
counterpart_role
Who you will be speaking with (e.g., "VP of Procurement", "Direct Report").
user_role
Your role in the conversation (e.g., "Account Executive", "Engineering Manager").

Resources

1 advertised

agent-protocol — Atlas Primer Agent Protocol & Scenario Engineering Guide

Advertised by the server during the last successful anonymous check.

Specification for designing high-stakes conversational voice simulations, behavioral resistance traits, and success criteria on Atlas Primer.

agent-protocol URI
atlasprimer://docs/agent-protocol

MIME type: text/markdown

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

  1. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
680 ms
95th percentile latency
680 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 680 ms · metadata changed · 1 tool(s), 1 resource(s), 1 prompt(s); warnings: Advertises resources/templates/list but does not implement it

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http atlas-primer-mcp https://roleplay.atlasprimer.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add atlas-primer-mcp --url https://roleplay.atlasprimer.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable atlas-primer-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "atlas-primer-mcp": {
      "url": "https://roleplay.atlasprimer.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "atlas-primer-mcp": {
      "type": "streamableHttp",
      "url": "https://roleplay.atlasprimer.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start atlas-primer-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "atlas-primer-mcp": {
      "type": "http",
      "url": "https://roleplay.atlasprimer.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http atlas-primer-mcp https://roleplay.atlasprimer.com/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://roleplay.atlasprimer.com/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "atlas-primer-mcp": {
      "serverUrl": "https://roleplay.atlasprimer.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Atlas Primer MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 5,530