Productivity

branchly.io

Provides a knowledge base API for managing content nodes, including listing, creating, reading, updating, and retrieving application configuration.

1 endpoint33 known toolsFirst detected August 31, 2026Last detected August 31, 2026

ENDPOINT 1

https://api.branchly.io/mcp

No auth detected

MCP server metadata

Name: branchly-mcp-server
Version: 0.1.0

Capabilities

experimentalloggingprompts.listChangedresources.listChangedtools.listChangedextensions.io.modelcontextprotocol/ui

Known tools 33

get_application

Return the full configuration of the authenticated application.

Inferred read-only

list_nodes

List nodes in the knowledge base.

Inferred read-only

create_node

Create a new content node in the knowledge base.

Potential side effects

read_node

Read a node by its ID.

Inferred read-only

update_node

Update a content node by its ID.

Potential side effects

list_data_sources

List data sources for the authenticated application.

Inferred read-only

update_data_source

Update a data source by its ID.

Potential side effects

list_prompts

List prompts for the authenticated application.

Inferred read-only

create_prompt

Create a new prompt version for the authenticated application.

Potential side effects

update_prompt

Activate or deactivate a prompt by its ID.

Inferred read-only

list_tools

List tools configured for the authenticated application.

Inferred read-only

read_tool

Read a tool by its ID.

Inferred read-only

update_tool

Update an existing tool by its ID.

Potential side effects

read_sessions

List sessions for application.

Inferred read-only

read_session_detail

Read a single session with its full history in token-dense form.

Inferred read-only

get_active_sessions_over_time

Time series of active sessions, bucketed by day or week (auto-chosen from the time window).

Inferred read-only

get_top_locales

Top locales (BCP-47 style, e.

Inferred read-only

get_top_languages

Top detected natural languages of user CHAT questions, ranked by occurrence count.

Inferred read-only

get_top_devices

Top device categories (e.

Inferred read-only

get_top_geographies

Top (country, region) combinations across all request types, ranked by occurrence count.

Inferred read-only

get_sentiment_distribution

Sentiment distribution of chat answers as counts of 'positive', 'negative', and 'neutral'.

Inferred read-only

get_top_cited_sources

Knowledge-base nodes most frequently cited in chat answers, ranked by citation count.

Inferred read-only

get_top_clicked_urls

URLs users actually clicked from inside the embed (search results, citation links, follow-ups, etc.

Inferred read-only

get_top_interaction_sources

Page URLs the user was ON when they interacted with the embed (chat, search, navigation, form submission), ranked by occurrence count.

Inferred read-only

get_top_searches

Top user search queries (normalized: lowercased, trimmed), ranked by occurrence count.

Inferred read-only

get_top_tags

Top tags attached to chat answers (auto-derived classifications), ranked by occurrence count.

Inferred read-only

get_answer_type_distribution

Distribution of chat answer types (e.

Inferred read-only

get_trending_classifications

Time series of trending classifications (topics OR intents inferred from chat content), one series per classification id.

Inferred read-only

read_chat_request_documents

Read the full document chunks retrieved for a single chat request (QA or SA).

Inferred read-only

read_chat_request_tool_calls

Read the full tool calls executed for a single chat request.

Inferred read-only

read_search_request_results

Read the full search results returned for a single instant-search request.

Inferred read-only

get_active_sessions_by_embed

Time series of active sessions broken down by embed type (chat, chat_widget, navigator, search_interface, voice, api).

Inferred read-only

update_chat_request_analytics

Update analytics fields on a chat request: summary, tags, answer_type, sentiment, classification_topic_id, or classification_intent_id.

Potential side effects

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.branchly-mcp-server]
url = "https://api.branchly.io/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "branchly-mcp-server": {
      "type": "http",
      "url": "https://api.branchly.io/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: branchly-mcp-server
Remote MCP URL: https://api.branchly.io/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "branchly-mcp-server": {
      "url": "https://api.branchly.io/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "branchly-mcp-server": {
      "type": "http",
      "url": "https://api.branchly.io/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "branchly-mcp-server",
  "transport": "streamable-http",
  "url": "https://api.branchly.io/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.