A
exa
exa is grade A with no findings: 39 rules ran across 9 surfaces and 2 tools, and nothing matched. 7 requests made. 0 penalty points — the scale counts problems, so zero is the best possible result.
What we found
Nothing matched. That is a statement about what could be seen, listed below — not a guarantee this server is clean.
What we tested
server_instructions
text the server sends at connect, before any tool is called
3 items checked · nothing matched
exa-search-serverExahttps://exa.ai
tool_name
the names of the tools
2 items checked · nothing matched
web_search_exaweb_fetch_exa
tool_description
what each tool says it does
2 items checked · nothing matched
tools/web_search_exa.descriptionSearch the web for any topic and get clean, ready-to-use content.
Best for: Finding current information, news, facts, people, companies, or answering questions about any topic.
Returns: Clean text content from top search results.
Query tips:
describe the ideal page, not keywords. "blog post comparing React and Vue performance" not "React vs Vue".
Use category:people / category:company to search through Linkedin profiles / companies respectively.
If highlights are insufficient, follow up with web_fetch_exa on the best URLs.
tools/web_fetch_exa.descriptionRead a webpage's full content as clean markdown. Use after web_search_exa when highlights are insufficient or to read any URL.
Best for: Extracting full content from known URLs. Batch multiple URLs in one call.
Returns: Clean text content and metadata from the page(s).
tool_input_schema
the descriptions on each tool’s input fields
5 items checked · nothing matched
tools/web_search_exa.inputSchema.properties.query.descriptionNatural language search query. Should be a semantically rich description of the ideal page, not just keywords. Optionally include category:<type> (company, people) to focus results — e.g. 'category:people John Doe software engineer'.
tools/web_search_exa.inputSchema.properties.numResults.descriptionNumber of search results to return (default: 10).
tools/web_search_exa.inputSchema.properties.objective.descriptionGoal for this search turn; say which documents should rank first, which should be excluded, and what specific facts or figures to pull from them.
tools/web_fetch_exa.inputSchema.properties.urls.descriptionURLs to read. Batch multiple URLs in one call.
tools/web_fetch_exa.inputSchema.properties.maxCharacters.descriptionMaximum characters to extract per page (default: 3000)
prompt_description
the descriptions of the server’s prompts
1 item checked · nothing matched
Get help with web search using Exa
prompt_message
the text inside those prompts
1 item checked · nothing matched
prompts/web_search_help -> messages[0].content.textI want to search the web for current information. Can you help me search for recent news about artificial intelligence breakthroughs?
resource_description
the descriptions of the server’s resources
1 item checked · nothing matched
List of available Exa tools and their descriptions
resource_contents
the contents of those resources
1 item checked · nothing matched
resources/exa://tools/list -> contents[0].text[
{
"id": "web_search_exa",
"name": "Web Search (Exa)",
"description": "Real-time web search using Exa AI",
"enabled": true
},
{
"id": "web_search_advanced_exa",
"name": "Advanced Web Search (Exa)",
"description": "Advanced web search with full Exa API control including category filters, domain restrictions, date ranges, highlights, summaries, and subpage crawling",
"enabled": false
},
{
"id": "get_code_context_exa",
"name": "Code Context Search (Deprecated)",
"description": "Deprecated: Use web_search_exa instead. Search for code snippets, examples, and documentation from open source repositories",
"enabled": false
},
{
"id": "company_research_exa",
"name": "Company Research (Deprecated)",
"description": "Deprecated: Use web_search_advanced_exa instead. Research companies and organizations",
"enabled": false
},
{
"id": "web_fetch_exa",
"name": "Web Crawling",
"description": "Extract content from specific URLs",
"enabled": true
},
{
"id": "deep_researcher_start",
"name": "Deep Researcher Start (Deprecated)",
"description": "Deprecated: Start a comprehensive AI research task",
"enabled": false
},
{
"id": "deep_researcher_check",
"name": "Deep Researcher Check (Deprecated)",
"description": "Deprecated: Check status and retrieve results of research task",
"enabled": false
},
{
"id": "people_search_exa",
"name": "People Search (Deprecated)",
"description": "Deprecated: Use web_search_advanced_exa instead. Search for people and professional profiles",
"enabled": false
},
{
"id": "linkedin_search_exa",
"name": "LinkedIn Search (Deprecated)",
"description": "Deprecated: Use web_search_advanced_exa instead",
"enabled": false
},
{
"id": "deep_search_exa",
"name": "Deep Search (Deprecated)",
"description": "Deprecated: Use web_search_advanced_exa instead. Deep search with query expansion and synthesized answers (requires API key)",
"enabled": false
},
{
"id": "crawling_exa",
"name": "Web Crawling (Deprecated)",
"description": "Deprecated: Use web_fetch_exa instead. Extract content from specific URLs",
"enabled": false
},
{
"id": "agent_run",
"name": "Run Exa Agent",
"description": "Run an Exa Agent for multi-step research, list-building, enrichment, or structured output. Returns the final output or a run ID for retained-run continuation.",
"enabled": false
}
]
Tools 2 probed of 2
Requests 7
Protocol 2025-11-25
Layers deterministic, structural, 1 model
AI read: claude-opus-5 examined 17 of 17 pieces of text, nothing to add.
Tested and not found: Concealment · Consent bypass · Persona / role override · Model-directed imperative · Result-as-instruction · Promotional · Upgrade / pricing URL · Structural signal
Details & raw data
mcp-audit scan-file data/snapshots/exa/2026-09-18T00-10-04Z/manifest.json
data/snapshots/exa/2026-09-18T00-10-04Z/manifest.json- findings.json — every published entry, machine-readable
| Manifest hash | sha256:385959804b07d333a0185b7284472ca6e9ede96b6356bfcfd7b86626709678ef |
|---|---|
| Ruleset hash | sha256:d26757507f22c9f8c437d7428a5ed19a46c3783c46f9ceb158b58a053eab1397 |
| Scanner | 0.1.0 |
| Scanned at | 2026-09-18T00:10:28.494Z |
Not covered: NON-DETERMINISTIC: two identical calls to "web_fetch_exa" returned different text. Content that changes between identical requests is a signal worth reading the snapshots for. SESSION-DEPENDENT: "web_search_exa" returned different text when the identical call was repeated later in the same session. Content that changes with session state, rather than with the request, is worth reading the snapshots for.