TwikitSAFE
A Model Context Protocol (MCP) server for interacting with Twitter.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://smithery.ai/server/mcp-twikit) A Model Context Protocol (MCP) server for interacting with Twitter.
Installation
Installing via Smithery
To install Twikit Twitter Search for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install mcp-twikit --client claude
Manual Installation
{
"mcpServer": {
"command": "uvx",
"args": ["--from", "git+https://github.com/adhikasp/mcp-twikit", "mcp-twikit"],
"env": {
"TWITTER_USERNAME": "@example",
"TWITTER_EMAIL": "[email protected]",
"TWITTER_PASSWORD": "secret",
}
}
}Example usage
Using mcp-client-cli
Comparing sentiments across different twitter accounts
$ llm compare 20 latest tweet directed @IndiHomeCare, @di_cbn, @BiznetHome, @ID_MyRepublic. What are people sentiment to the product? Do 1 search for each account I'll help you analyze the latest tweets for these internet service providers in Indonesia to understand the public sentiment. I'll use the search_twitter function for each account. Tool Calls: search_twitter Args: query: to:IndiHomeCare count: 20 sort_by: Latest Tool Calls: search_twitter Args: query: to:di_cbn count: 20 sort_by: Latest Tool Calls: search_twitter Args: query: to:BiznetHome count: 20 sort_by: Latest Tool Calls: search_twitter Args: query: to:ID_MyRepublic count: 20 sort_by: Latest Sentiment Analysis Summary: 1. IndiHomeCare: - Predominantly Negative Sentiment - Key Issues: - Unstable internet connection - Slow response times - Intermittent service disruptions
3f1b77aea2a4OBSERVED · 2026-10-06Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-twikit --env TWITTER_PASSWORD=${TWITTER_PASSWORD} -- uvx mcp-twikit{
"mcpServers": {
"mcp-twikit": {
"command": "uvx",
"args": [
"mcp-twikit"
],
"env": {
"TWITTER_PASSWORD": "${TWITTER_PASSWORD}"
}
}
}
}Exposed tools (8)
4 read · 2 write · 2 destructive. Blast radius: 2 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
delete_dm | destructive | Delete a direct message by its ID. |
delete_tweet | destructive | Delete a tweet by its ID. |
get_latest_timeline | read | Get tweets from your home timeline (Following). |
get_timeline | read | Get tweets from your home timeline (For You). |
get_user_tweets | read | Get tweets from a specific user |
post_tweet | write | Post a tweet with optional media, reply, and tags. |
search_twitter | read | Search twitter with a query. Sort by |
send_dm | write | Send a direct message to a user. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- UNDECLARED (1 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
delete_dm, delete_tweet
Gates applied: no_behavioural_pass.
3f1b77aea2a4full audit observations/trust-audit/mcp-server/adhikasp__twikit.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-06 | 3f1b77aea2a4 | SAFE | B | 89 | first audit |
Questions
What is the Twikit MCP server?
A Model Context Protocol (MCP) server for interacting with Twitter.
What tools does Twikit expose?
8 in total: 4 read-only, 2 that write, and 2 that can delete or overwrite (delete_dm, delete_tweet). Every one is listed on this page with its risk.
Is Twikit safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 2 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Twikit need?
It reads TWITTER_PASSWORD from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (3f1b77aea2a4), read on 2026-10-06. The repository is watched and re-audited when it changes.