A
licenseB
qualityD
maintenanceAn MCP server that allows Claude to create, manage and publish X/Twitter posts directly through the chat interface.
5
61
MIT
Twitter MCP Server
by EnesCinr
Servidor MCP de Twitter
Este servidor MCP permite a los clientes interactuar con Twitter, posibilitando la publicación de tweets y la búsqueda en Twitter.
Inicio rápido
Cree una cuenta de desarrollador de Twitter y obtenga sus claves API desde el Portal para desarrolladores de Twitter
Agregue esta configuración a su archivo de configuración de Claude Desktop:
Ventanas : %APPDATA%\Claude\claude_desktop_config.json
macOS : ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"twitter-mcp": {
"command": "npx",
"args": ["-y", "@enescinar/twitter-mcp"],
"env": {
"API_KEY": "your_api_key_here",
"API_SECRET_KEY": "your_api_secret_key_here",
"ACCESS_TOKEN": "your_access_token_here",
"ACCESS_TOKEN_SECRET": "your_access_token_secret_here"
}
}
}
}Reiniciar Claude Desktop
¡Listo! Claude ahora puede interactuar con Twitter mediante dos herramientas:
post_tweet: Publicar un nuevo tweetsearch_tweets: Buscar tweets
Related MCP server: twitter-mcp
Ejemplo de uso
Prueba a preguntarle a Claude:
"¿Puedes publicar un tweet que diga '¡Hola de Claude!'"?
"¿Puedes buscar tweets sobre Claude AI?"
Solución de problemas
Los registros se pueden encontrar en:
Windows :
%APPDATA%\Claude\logs\mcp-server-twitter.logmacOS :
~/Library/Logs/Claude/mcp-server-twitter.log
Desarrollo
Si deseas contribuir o ejecutar desde la fuente:
Clonar el repositorio:
git clone https://github.com/EnesCinr/twitter-mcp.git
cd twitter-mcpInstalar dependencias:
npm installConstruir:
npm run buildCorrer:
npm startEjecución de evaluaciones
El paquete evals carga un cliente mcp que ejecuta el archivo index.ts, por lo que no es necesario reconstruir entre pruebas. Puede cargar variables de entorno prefijando el comando npx. Puede encontrar la documentación completa aquí .
OPENAI_API_KEY=your-key npx mcp-eval src/evals/evals.ts src/index.tsLicencia
Instituto Tecnológico de Massachusetts (MIT)
Available Tools
2 toolspost_tweetB
Post a new tweet to Twitter
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | The content of your tweet | |
| reply_to_tweet_id | No | Optional: ID of the tweet to reply to |
TDQS
B3.3/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of disclosure. However, it only states the action without detailing any behavioral traits (e.g., authentication requirements, potential errors, rate limits, or that tweets are public). For a mutation tool, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise at a single sentence, with no superfluous words. It directly communicates the tool's purpose without any waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (2 parameters, no output schema), the description is minimally adequate but lacks details such as expected return value (e.g., tweet ID) or any error conditions. It covers the basic action but leaves gaps for practical use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, so the schema already details both parameters. The description adds no extra meaning beyond what the schema provides, so it meets the baseline of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Post a new tweet to Twitter', which is a specific verb ('post') and resource ('tweet'). It distinguishes itself from the sibling tool 'search_tweets' by focusing on creation rather than retrieval.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage guidance is provided. The description does not specify when to use this tool versus the sibling 'search_tweets', nor does it mention any prerequisites, limitations, or contextual conditions for posting a tweet.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_tweetsC
Search for tweets on Twitter
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query | |
| count | Yes | Number of tweets to return (10-100) |
TDQS
C2.8/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description must bear the full burden. However, it only says 'Search for tweets' without disclosing any behavioral traits such as read-only nature, permissions required, rate limits, or result format. This is minimal disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness3/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise with one sentence, but it lacks detail that could be included without significant bloat. While it is not verbose, it is also not optimally informative for its length.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of output schema and annotations, the description should compensate by explaining return values or usage constraints. It does not; it only states the basic operation, leaving many contextual gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already explains each parameter. The description does not add any additional meaning or context for the parameters beyond what the schema provides, so it meets the baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches for tweets on Twitter, which is a specific verb+resource. It distinguishes from the sibling tool 'post_tweet' implicitly (search vs. post), but does not explicitly state the difference.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus the sibling 'post_tweet' or any alternatives. The description simply states what it does, without context on appropriate usage scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
2 tool updates
v1.0.0- First observed
post_tweet - First observed
search_tweets
TDQS
B3.2/5.0
Scored across 2 tools
Disambiguation5/5
The two tools have clearly distinct purposes: one for posting tweets and one for searching tweets. There is no overlap in functionality.
Naming Consistency5/5
Both tool names follow the verb_noun pattern: 'post_tweet' and 'search_tweets'. The naming is consistent and predictable.
Tool Count3/5
With only 2 tools, the server feels thin for a Twitter API. It is borderline acceptable but lacks the breadth typically expected from a Twitter server.
Completeness2/5
The tool surface is severely incomplete. Missing fundamental operations like deleting tweets, liking, retweeting, or managing user interactions, which will cause agent failures.
Maintenance
ActivityInactive
ResponsivenessUnresponsive
Related MCP Connectors
Twitter/X read-only MCP server — 12 tools: search, users, tweets, followers, timelines, trends.
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
FastMCP server for posting formatted content to X (Twitter) — Tollbooth-monetized, DPYC-native
Augments MCP Server - A comprehensive framework documentation provider for Claude Code
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA lightweight Twitter MCP server for Claude Code with 17 tools for reading and writing tweets, including search, user profiles, and media uploads, using a hybrid API approach.14 npm2ISC
- AlicenseAqualityFmaintenanceA Model Context Protocol (MCP) server that provides access to Twitter data through the TwitterAPI.io service, enabling Claude and other MCP clients to interact with Twitter's ecosystem without requiring Twitter developer account approval.113 npm4MIT
- AlicenseNot gradedqualityCmaintenanceAn MCP server that enables posting tweets, reading timelines, searching posts, and interacting with X (Twitter) API.6 npm2MIT