TweetBinder by Audiense MCP Server
Allows Claude and other MCP-compatible AI models to access TweetBinder by Audiense analytics data, enabling analysis of hashtags, users, and conversations on Twitter/X with engagement metrics, sentiment analysis, and report generation.
AudienseCo
README
TweetBinder by Audiense MCP Server
This is a Model Context Protocol (MCP) server for the TweetBinder by Audiense API, allowing Claude and other MCP-compatible AI models to access TweetBinder by Audiense analytics data.
Features
- Access TweetBinder analytics directly from Claude
- Analyze hashtags, users, and conversations on Twitter/X
- Get engagement metrics, sentiment analysis, and more
- Create Twitter reports with custom search queries
- Check report generation status
- Retrieve detailed report statistics
- Get account balance and quota information
- Count tweets matching specific queries
- List and manage your TweetBinder reports
- Access tweet content and user information from reports
Installation
Installing via Smithery
To install mcp-tweetbinder for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @AudienseCo/mcp-tweetbinder --client claude
Manual Configuration
Prerequisites
- Node.js (v18 or higher)
- Claude Desktop App
- TweetBinder by Audiense account with API credentials
- Clone this repository
- Install dependencies:
npm install
- Build the project:
npm run build
You need a valid TweetBinder API Bearer Token to use this service. Set it in your environment:
export TWEETBINDER_API_TOKEN='your-bearer-token-here'
Usage with Claude Desktop
-
Edit your Claude Desktop configuration file:
- MacOS:
code ~/Library/Application\ Support/Claude/claude_desktop_config.json
- Windows:
code %AppData%\Claude\claude_desktop_config.json
- MacOS:
-
Add this configuration:
"mcpServers": {
"tweetbinder": {
"command": "node",
"args": [
"/absolute/path/to/build/index.js"
],
"env": {
"TWEETBINDER_API_TOKEN": "your-bearer-token-here"
}
}
}
- Restart Claude Desktop
Available Tools
create-twitter-report
Creates a new report that analyzes Twitter/X data based on a search query.
-
Parameters:
query
(string): The search query for Twitter data. Can include operators like AND, OR, hashtags, mentions, etc.limit
(number, optional): Maximum number of tweets to retrieve (up to 50,000).startDate
(number, optional): Start date as Unix timestamp (seconds since epoch).endDate
(number, optional): End date as Unix timestamp (seconds since epoch).reportType
(enum, optional): Type of report to create: "7-day" for last week or "historical" for all time. Default: "7-day".
-
Response:
- Report ID and status information for the created report.
- Instructions for checking report status and retrieving statistics.
create-twitter-count
Creates a new report that counts tweets matching a search query.
-
Parameters:
query
(string): The search query for Twitter data. Can include operators like AND, OR, hashtags, mentions, etc.reportType
(enum, optional): Type of report to create: "7-day" for last week or "historical" for all time. Default: "7-day".
-
Response:
- Raw JSON response containing:
status
: The status of the report creationresourceId
: The ID of the created reporterror
/message
: Any error or status messages
- Raw JSON response containing:
list-reports
Retrieves a list of all your TweetBinder reports with sorting capabilities.
-
Parameters:
order
(string, optional): Sorting parameter in the format 'field|direction'. Example: 'createdAt|-1' for newest first, 'createdAt|1' for oldest first.
-
Response:
- Raw JSON response containing an array of reports with details for each:
id
: Report IDname
: Report namestatus
: Current status (Generated, Waiting, etc.)createdAt
: Creation timestampupdatedAt
: Last update timestamptype
: Report typesource
: Report sourcequery
: Original search query
- Raw JSON response containing an array of reports with details for each:
get-report-content
Retrieves the actual tweets or users from a generated report with advanced filtering and pagination.
-
Parameters:
reportId
(string): The ID of the report to retrieve content for.contentType
(enum): The type of content to retrieve: 'tweets' for tweet data or 'users' for user data.page
(number, optional): Page number for pagination. Starts at 1.perPage
(number, optional): Number of items per page.sortBy
(string, optional): Field to sort by (e.g., 'createdAt', 'counts.favorites').sortDirection
(enum, optional): Sort direction: '1' for ascending, '-1' for descending.filter
(string, optional): JSON string with filter criteria. Example: '{"counts.favorites":{"$gt":10}}'
-
Response:
- Raw JSON response containing:
items
: Array of tweet or user objectspagination
: Information about total items and pages
When requesting tweets, detailed information is returned, including:
- Tweet ID, text, creation date, language
- Author details (name, username, followers, etc.)
- Engagement metrics (retweets, likes, replies, etc.)
- Media content (hashtags, images, links)
- Sentiment analysis
When requesting users, information includes:
- User ID, name, username
- Profile picture URL
- Follower and following counts
- Verification status
- User value and other metrics
- Raw JSON response containing:
Note: Report must be in 'Generated' status to access content. Use the get-report-status
tool to check if a report is ready.
Query Syntax Examples:
#apple
: Tweets containing the hashtag #appleapple lang:en
: English tweets containing "apple"(#apple OR #iphone) -#android
: Tweets with #apple or #iphone but not #android@apple
: Tweets mentioning @applefrom:apple
: Tweets posted by user "apple"
Note: After creating the count report, use the get-report-status
tool to check when it's ready, then use get-report-stats
to get the actual count.
get-report-status
Checks the current status of a TweetBinder report.
-
Parameters:
reportId
(string): The ID of the report to check.
-
Response:
- The current status of the report, which can be one of:
- Generated: The report is complete and ready to use.
- Waiting: The report is still being generated or waiting for tweets to be collected.
- Outdated: The report is being updated with new data and will be available soon.
- Deleted: The report has been deleted and is no longer available.
- Archived: The report has been archived and may be deleted soon.
- An explanation of what the status means and what actions are available.
- The current status of the report, which can be one of:
Note: You must first create a report using the create-twitter-report
or create-twitter-count
tool to get a report ID.
get-report-stats
Retrieves comprehensive statistics and analytics for a TweetBinder report.
-
Parameters:
reportId
(string): The ID of the report to retrieve statistics for.
-
Response:
- A formatted summary of the report statistics including:
- Overview: Total tweets, date range, contributors, engagement, media, and links.
- Engagement Metrics: Potential reach, impressions, retweets, and likes.
- Sentiment Analysis: Overall sentiment score and interpretation.
- Top Contributors: Most active users and their tweet counts.
- Popular Content: Most retweeted posts.
- Frequently Used Hashtags: Common hashtags used in the conversation.
- A formatted summary of the report statistics including:
Note: The report must have "Generated" status before statistics can be retrieved. Use the get-report-status
tool to check if a report is ready.
get-account-balances
Retrieves information about your account's credit balance, usage, and remaining quota.
-
Parameters:
- None
-
Returns:
- Raw JSON response containing:
total
: Total credits availableused
: Credits usedavailable
: Credits currently availablediscount
: Any applicable discountremainingReports
: Number of reports remainingquota
: Quota information including:startedAt
: Quota period start datefinishedAt
: Quota period end dateremaining
: Remaining quotaused
: Used quotatotal
: Total quota
- Any error or status messages
- Raw JSON response containing:
Troubleshooting
Tools Not Appearing in Claude
- Check Claude Desktop logs:
tail -f ~/Library/Logs/Claude/mcp*.log
- Verify environment variables are set correctly.
- Ensure the absolute path to index.js is correct.
Authentication Issues
- Double-check credentials.
- Ensure the refresh token is still valid.
- Verify that the required API scopes are enabled and that you have enough credits.
Viewing Logs
To check server logs:
For MacOS/Linux:
tail -n 20 -f ~/Library/Logs/Claude/mcp*.log
For Windows:
Get-Content -Path "$env:AppData\Claude\Logs\mcp*.log" -Wait -Tail 20
Security Considerations
- Keep API credentials secure – never expose them in public repositories.
- Use environment variables to manage sensitive data.
📄 License
This project is licensed under the Apache 2.0 License. See the LICENSE file for more details.
Recommended Servers
Crypto Price & Market Analysis MCP Server
A Model Context Protocol (MCP) server that provides comprehensive cryptocurrency analysis using the CoinCap API. This server offers real-time price data, market analysis, and historical trends through an easy-to-use interface.
MCP PubMed Search
Server to search PubMed (PubMed is a free, online database that allows users to search for biomedical and life sciences literature). I have created on a day MCP came out but was on vacation, I saw someone post similar server in your DB, but figured to post mine.
dbt Semantic Layer MCP Server
A server that enables querying the dbt Semantic Layer through natural language conversations with Claude Desktop and other AI assistants, allowing users to discover metrics, create queries, analyze data, and visualize results.
mixpanel
Connect to your Mixpanel data. Query events, retention, and funnel data from Mixpanel analytics.

Sequential Thinking MCP Server
This server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.

Nefino MCP Server
Provides large language models with access to news and information about renewable energy projects in Germany, allowing filtering by location, topic (solar, wind, hydrogen), and date range.
Vectorize
Vectorize MCP server for advanced retrieval, Private Deep Research, Anything-to-Markdown file extraction and text chunking.
Mathematica Documentation MCP server
A server that provides access to Mathematica documentation through FastMCP, enabling users to retrieve function documentation and list package symbols from Wolfram Mathematica.
kb-mcp-server
An MCP server aimed to be portable, local, easy and convenient to support semantic/graph based retrieval of txtai "all in one" embeddings database. Any txtai embeddings db in tar.gz form can be loaded
Research MCP Server
The server functions as an MCP server to interact with Notion for retrieving and creating survey data, integrating with the Claude Desktop Client for conducting and reviewing surveys.