> For the complete documentation index, see [llms.txt](https://docs.storylane.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.storylane.io/mcp/storylane-mcp/repx-tools.md).

# RepX Tools

Read what buyers are asking your agents, which accounts engaged, and how RepX is performing.

Jump ahead:

* [Agents](#agents)
* [Performance](#performance)
* [Buyers](#buyers)
* [What you cannot do (yet)](#what-you-cannot-do-over-mcp)

#### Agents

* `repx_list_agents` — List the RepX agents in the workspace. Returns each agent's ID, name, base link, and branding colour. Start here when you have more than one agent and need an ID for other queries.

#### Performance

* `repx_get_stats` — Workspace-level totals: sessions, qualified sessions, CTA opens, leads captured, median session duration, and total time in conversation. The fastest way to answer "how is RepX doing".
* `repx_get_analytics` — Session-level records, 25 per page. Each session includes the AI-written conversation summary, intent level, duration, device and platform, extracted variables such as email and qualification status, the matched lead and its CRM IDs, and the topics discussed.
* `repx_get_analytics_detailed` — Extended session detail. Use when `repx_get_analytics` does not carry the field you need.

{% hint style="info" %}
`repx_get_analytics` returns personal data, including lead names, email addresses, IP addresses, and CRM contact IDs. It is also the largest response in the MCP surface. Narrow your prompt to a date range, an agent, or a handful of sessions rather than asking for everything.
{% endhint %}

#### Buyers

* `repx_list_topics` — Every topic buyers have raised with your agents, with a session count for each. The quickest way to see what your market is actually asking about.
* `repx_list_accounts` — Companies that have had a RepX conversation, with engagement data.
* `repx_list_leads` — Leads captured by RepX, including the agent and conversation they came from.

{% hint style="info" %}
Topic names can repeat with different IDs where topics were created separately. Group by name rather than ID when you want a single count per subject.
{% endhint %}

#### What you cannot do over MCP (yet)

* Create, clone, or delete agents
* Edit Playbooks, qualification criteria, or guardrails
* Change an agent's knowledge sources
* Send or reply to a conversation

Configure agents in Storylane, then use MCP to interrogate what they produce.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.storylane.io/mcp/storylane-mcp/repx-tools.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
