Low Risk

searchTweetsAdvanced

Search for tweets using advanced query operators and filters. Each page returns approximately 20 tweets. Use cursor for pagination. ## Available Search Operators ### Basic Operators - `watching now` - containing both "watching" and "now" (default AND operator) - `"happy hour"` - containing the ...

Accepts freeform code/query input (query); Admin/system-level operation

Part of the Tweet Search MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

janwilmake/x-search-mcp Read Risk 2/5

AI agents call searchTweetsAdvanced to retrieve information from Tweet Search without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though searchTweetsAdvanced only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

janwilmake-x-search-mcp.yaml
tools:
  searchTweetsAdvanced:
    rules:
      - action: allow

See the full Tweet Search policy for all 1 tools.

Tool Name searchTweetsAdvanced
Category Read
Risk Level Low

Agents calling read-class tools like searchTweetsAdvanced have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.

What does the searchTweetsAdvanced tool do? +

Search for tweets using advanced query operators and filters. Each page returns approximately 20 tweets. Use cursor for pagination. ## Available Search Operators ### Basic Operators - `watching now` - containing both "watching" and "now" (default AND operator) - `"happy hour"` - containing the exact phrase "happy hour" - `love OR hate` - containing either "love" or "hate" (or both) - `beer -root` - containing "beer" but not "root" ### Hashtags and Mentions - `#haiku` - containing the hashtag "haiku" - `@NASA` - mentioning Twitter account "NASA" ### User-specific Searches - `from:interior` - sent from Twitter account "interior" - `to:NASA` - a Tweet authored in reply to Twitter account "NASA" - `list:NASA/astronauts-in-space-now` - sent from accounts in the specified Twitter list ### Media Filters - `puppy filter:media` - containing "puppy" and an image or video - `puppy filter:native_video` - containing "puppy" and an uploaded video, Amplify video, Periscope, or Vine - `puppy filter:periscope` - containing "puppy" and a Periscope video URL - `puppy filter:vine` - containing "puppy" and a Vine - `puppy filter:images` - containing "puppy" and links identified as photos, including third parties - `puppy filter:twimg` - containing "puppy" and a pic.twitter.com link - `puppy -filter:retweets` - containing "puppy", filtering out retweets ### Link Filters - `hilarious filter:links` - containing "hilarious" and linking to URL - `puppy url:amazon` - containing "puppy" and a URL with "amazon" anywhere within it ### Date Filters - `superhero since:2015-12-21` - containing "superhero" and sent since date "2015-12-21" (year-month-day format) - `puppy until:2015-12-21` - containing "puppy" and sent before date "2015-12-21" ### Sentiment Filters - `movie -scary :)` - containing "movie", not "scary", with positive attitude - `flight :(` - containing "flight" with negative attitude - `traffic ?` - containing "traffic" and asking a question ## Query Examples - `"AI" OR "Twitter" from:elonmusk since:2021-12-31` - `#bitcoin filter:media -filter:retweets` - `"climate change" lang:en filter:links` - `from:NASA filter:images :)` **Note:** Make sure to URL encode queries. Space characters can be represented by "%20" or "+".. It is categorised as a Read tool in the Tweet Search MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on searchTweetsAdvanced? +

Add a rule in your Intercept YAML policy under the tools section for searchTweetsAdvanced. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Tweet Search MCP server.

What risk level is searchTweetsAdvanced? +

searchTweetsAdvanced is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit searchTweetsAdvanced? +

Yes. Add a rate_limit block to the searchTweetsAdvanced rule in your Intercept policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block searchTweetsAdvanced completely? +

Set action: deny in the Intercept policy for searchTweetsAdvanced. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides searchTweetsAdvanced? +

searchTweetsAdvanced is provided by the Tweet Search MCP server (janwilmake/x-search-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policies on Tweet Search

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept
github.com/policylayer/intercept →
// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.