Skip to main content
hc
Submit
mcpSource-backed
Exa logo

Exa MCP Server

Web search and web fetch MCP server that connects AI assistants to Exa's hosted search, crawling, code search, and research capabilities.

by Exa Labs · submitted by oktofeesh1·added 2026-06-05·
Claude CodeCodexCursorClaude Desktop
HarnessClaude CodeCodexCursorClaude Desktop
Review first — review before installing

Open the source and read safety notes before installing.

Citation facts

Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.

Canonical URL
https://heyclau.de/entry/mcp/exa-mcp-server
Source URLs
https://exa.ai/docs/reference/exa-mcp, https://github.com/exa-labs/exa-mcp-server, https://exa.ai
Brand
Exa
Brand domain
exa.ai
Brand asset source
brandfetch
Safety notes
Web search and fetch results may be incomplete, stale, biased, or adversarial; verify important claims against primary sources., Fetching pages can retrieve untrusted web content that may contain prompt injection or malicious instructions., Advanced search filters and domain targeting should be reviewed when used for compliance, hiring, due diligence, or security research., Protect Exa API keys and avoid placing real keys in shared config files, screenshots, logs, or prompts.
Privacy notes
Search queries, fetched URLs, tool parameters, page contents, API keys, and surrounding prompts may be sent to Exa and the MCP client., Research topics can reveal product plans, customers, vulnerabilities, hiring activity, legal matters, or personal interests., Review Exa's current data handling, account, and rate-limit policies before using it with proprietary or regulated workflows.
Author
Exa Labs
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-05

Decision playbook

Review trust signals before you adopt

Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.

Compare context
Selected

0

Current score

63

Baseline

—

Delta

No baseline selected

No major trust-signal divergence detected in the current selection.

Source and provenance checks

Needs review

Confirm ownership and provenance before trusting install instructions.

  • Source link availableRequired

    Open the canonical repository and verify ownership.

    Done

  • Source provenance statusRequired

    Marked as source-backed.

    Done

  • Metadata reviewed

    No reviewed flag detected in metadata.

    Pending

Safety and privacy checks

Complete

Validate risk disclosures before installation or API wiring.

  • Safety notes presentRequired

    Review the listed safety guidance before running commands.

    Done

  • Privacy notes presentRequired

    Review data handling notes before connecting accounts or secrets.

    Done

  • Trust level risk gateRequired

    Trust level does not block evaluation.

    Done

Package and install checks

Needs review

Check package metadata and artifact integrity signals.

  • Install payload available

    Install or copy payload is available for review.

    Done

  • Package verification flag

    No package verification flag provided.

    Pending

  • Checksum metadata

    No checksum provided for downloaded artifact.

    Pending

Compare-driven decision checks

Needs review

Use compare context to validate trade-offs before adoption.

  • Compare tray has multiple entries

    Add at least one more entry to compare trust differences.

    Pending

  • Baseline comparison available

    No baseline peer selected yet.

    Pending

  • Diverging trust signals identified

    No major trust-signal divergence found.

    Pending

Setup at a glance

CLI install

Copy-ready — paste the snippet to get started.

5 minutes

Install command

Provided

Config snippet

Provided

Copy snippet

Provided

Prerequisites

3 to clear

Platforms

4 listed

Install type

CLI install

Adoption plan

Balanced adoption plan

Current risk score 24/100. Use staged verification before broader rollout.

Risk 24

Pre-adoption checks

Validate source and review signals before any execution.

  • Confirm source provenanceRequired

    Source URL/provenance metadata is present.

    Done

  • Confirm metadata review state

    No review metadata found; increase manual validation.

    Pending

  • Verify install payload

    Install/config payload exists and can be inspected.

    Done

Security checks

Confirm safety, privacy, and package integrity signals.

  • Review safety notesRequired

    Safety notes are present.

    Done

  • Review privacy notesRequired

    Privacy notes are present.

    Done

  • Verify package integrity metadata

    No package verification/checksum metadata.

    Pending

Rollout

Adopt in controlled steps based on the selected plan.

  • Run in isolated sandbox firstRequired

    Use a constrained sandbox and observe behavior across multiple tasks.

    Pending

  • Roll out graduallyRequired

    Roll out to a small cohort before wider usage.

    Pending

  • Set monitoring and fallback

    Define rollback path and monitor errors after adoption.

    Pending

Evidence readiness

Evidence readiness matrix · balanced

Missing required evidence: Metadata review. Risk score 31.

Risk 31

Source provenance

Present

Source repository/provenance is listed.

Required in this preset

Metadata review

Missing

Review metadata is missing.

Required in this preset

Safety notes

Present

Safety notes are present.

Required in this preset

Privacy notes

Present

Privacy notes are present.

Optional in this preset

Package integrity

Missing

Package integrity metadata is missing.

Optional in this preset

Install payload

Present

Install payload is available.

Required in this preset

Required gaps: Metadata review

Decision timeline

Decision timeline · balanced

Blocking gaps: Check metadata review status. Risk 28.

Risk 28

triage

Confirm source provenanceRequired

Source/provenance metadata is available.

Done

triage

Check metadata review statusRequired

Review metadata is missing.

Pending

verify

Review safety notesRequired

Safety notes are available.

Done

verify

Review privacy notes

Privacy notes are available.

Done

verify

Validate package integrity metadata

Package integrity metadata is missing.

Pending

rollout

Verify install payload and commandsRequired

Install payload is available.

Done

Blockers: Check metadata review status

Prerequisite readiness

Prerequisite readiness

3 prerequisites to line up before setup. Have accounts and credentials ready first.

0/3 ready
Account & credentials1Network & hosting25 minutes

Safety & privacy surface

Safety & privacy surface

4 safety and 3 privacy notes across 2 risk areas. Review closely: credentials & tokens.

2 areas
  • SafetyGeneralWeb search and fetch results may be incomplete, stale, biased, or adversarial; verify important claims against primary sources.
  • SafetyGeneralFetching pages can retrieve untrusted web content that may contain prompt injection or malicious instructions.
  • SafetyGeneralAdvanced search filters and domain targeting should be reviewed when used for compliance, hiring, due diligence, or security research.
  • SafetyCredentials & tokensProtect Exa API keys and avoid placing real keys in shared config files, screenshots, logs, or prompts.
  • PrivacyCredentials & tokensSearch queries, fetched URLs, tool parameters, page contents, API keys, and surrounding prompts may be sent to Exa and the MCP client.
  • PrivacyGeneralResearch topics can reveal product plans, customers, vulnerabilities, hiring activity, legal matters, or personal interests.
  • PrivacyGeneralReview Exa's current data handling, account, and rate-limit policies before using it with proprietary or regulated workflows.

Safety notes

  • Web search and fetch results may be incomplete, stale, biased, or adversarial; verify important claims against primary sources.
  • Fetching pages can retrieve untrusted web content that may contain prompt injection or malicious instructions.
  • Advanced search filters and domain targeting should be reviewed when used for compliance, hiring, due diligence, or security research.
  • Protect Exa API keys and avoid placing real keys in shared config files, screenshots, logs, or prompts.

Privacy notes

  • Search queries, fetched URLs, tool parameters, page contents, API keys, and surrounding prompts may be sent to Exa and the MCP client.
  • Research topics can reveal product plans, customers, vulnerabilities, hiring activity, legal matters, or personal interests.
  • Review Exa's current data handling, account, and rate-limit policies before using it with proprietary or regulated workflows.

Prerequisites

  • MCP client with hosted or remote MCP support, or mcp-remote for clients that need a stdio bridge.
  • Exa API key for higher limits, production usage, or npm-package configuration.
  • Network access to the Exa hosted MCP endpoint and target webpages.

Schema details

Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
5 minutes
Difficulty
beginner
Tool listing metadata
Full copyable content
{
  "mcpServers": {
    "exa": {
      "url": "https://mcp.exa.ai/mcp"
    }
  }
}

About this resource

Content

Exa MCP Server connects MCP clients to Exa's web search and page-fetching capabilities. It can be used as a hosted remote MCP server or through the exa-mcp-server npm package with an Exa API key.

The current README and docs emphasize web search, web fetch, and advanced web search tools, with deprecated tool names retained for backwards compatibility. The hosted endpoint has setup examples for Cursor, VS Code, Claude Code, Claude Desktop, Codex, OpenCode, Antigravity, Windsurf, Zed, Gemini CLI, v0, Warp, Kiro, Roo Code, and other clients.

Source Review

These sources were reviewed on 2026-06-05. Prefer the live docs for current hosted endpoint behavior, API key options, enabled tools, deprecated tools, rate limits, and client-specific setup.

Features

  • Hosted remote MCP endpoint for clients with remote MCP support.
  • Stdio bridge support through mcp-remote.
  • npm package option for API-key-backed local configuration.
  • web_search_exa for web search with clean result content.
  • web_fetch_exa for fetching full content from known URLs.
  • Optional web_search_advanced_exa for filters, domains, dates, and content options.
  • Setup examples for many MCP clients and AI editors.

Installation

For clients that support hosted MCP endpoints, add Exa directly:

{
  "mcpServers": {
    "exa": {
      "url": "https://mcp.exa.ai/mcp"
    }
  }
}

For clients that need a stdio bridge, use mcp-remote:

{
  "mcpServers": {
    "exa": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.exa.ai/mcp"]
    }
  }
}

For npm-package usage, follow the README and provide EXA_API_KEY through your client's environment configuration.

Use Cases

  • Search for recent API documentation, changelog notes, or implementation examples.
  • Fetch and summarize a known webpage from a model-assisted workflow.
  • Ground research prompts in fresh web content before drafting a report.
  • Use advanced search filters to narrow results by domain or recency.
  • Give coding agents live search context without building a custom search tool.

Safety and Privacy

Web content can contain prompt injection, incorrect claims, or malicious instructions. Keep model instructions separate from fetched content and verify important answers against primary sources.

Search queries and fetched URLs can reveal sensitive research topics. Protect API keys and review Exa's current privacy and retention posture before using this server with proprietary, regulated, or customer-specific work.

Duplicate Check

No exa-labs/exa-mcp-server entry or source URL was found in content/mcp. This entry is separate from Tavily, Perplexity, Firecrawl, and other search or crawling MCP servers because it covers Exa's hosted endpoint and npm package.

#search#research#web#crawling#remote

Source citations

Add this badge to your README

Show that Exa MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/mcp/exa-mcp-server.svg)](https://heyclau.de/entry/mcp/exa-mcp-server)

How it compares

Exa MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

Field
Exa logoExa MCP Server

Web search and web fetch MCP server that connects AI assistants to Exa's hosted search, crawling, code search, and research capabilities.

Open dossier
DuckDuckGo MCP Server

MCP server that gives Claude DuckDuckGo web search plus webpage content fetching and parsing tools.

Open dossier
open-webSearch MCP Server

No-key multi-engine MCP server, CLI, and local daemon for web search and public web content retrieval across engines such as Bing, DuckDuckGo, Brave, Exa, Baidu, CSDN, Juejin, Startpage, and Sogou.

Open dossier
Kagi MCP Server logoKagi MCP Server

Official Kagi MCP server that gives Claude web, news, video, podcast, image, and page-extraction tools backed by the Kagi Search and Extract APIs.

Open dossier
Next steps
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Trust
Review statusNot reviewedNot reviewedNot reviewedNot reviewed
Package trustPackage not verifiedPackage not verifiedPackage not verifiedPackage not verified
Source provenanceSource-backedSource-backedSource-backedSource-backed
Submitteroktofeesh1oktofeesh1oktofeesh1oktofeesh1
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
BrandExa logoExa——Kagi MCP Server logoKagi MCP Server
Categorymcpmcpmcpmcp
SourceSource-backedSource-backedSource-backedSource-backed
AuthorExa LabsNick ClydeAas-eeKagi Search
Added2026-06-052026-06-052026-06-062026-06-06
Platforms
Claude CodeCodexCursorClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Harness
Claude CodeCodexCursorClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Source repo————
Safety notes✓Web search and fetch results may be incomplete, stale, biased, or adversarial; verify important claims against primary sources. Fetching pages can retrieve untrusted web content that may contain prompt injection or malicious instructions. Advanced search filters and domain targeting should be reviewed when used for compliance, hiring, due diligence, or security research. Protect Exa API keys and avoid placing real keys in shared config files, screenshots, logs, or prompts.✓DuckDuckGo MCP Server can search the web and fetch arbitrary webpages requested through the MCP client. Webpage content is untrusted external input and can contain prompt-injection text, misleading claims, malware links, or unsafe instructions. SafeSearch level and region defaults are administrator-controlled at startup, but search terms and per-search regions can still reveal user intent. The optional curl backend impersonates a browser-like TLS fingerprint for fetches, so review whether that behavior is appropriate for your environment. Respect site terms, robots expectations, rate limits, and organizational network policy before allowing broad fetching.✓open-webSearch can send search queries to multiple public engines and fetch public web pages, GitHub READMEs, CSDN articles, Juejin articles, and other supported targets. Search and fetch results can be incomplete, stale, rate-limited, blocked, region-dependent, or affected by search-engine ranking and scraping protections. Respect each target site's terms and robots expectations; do not use the server for abusive scraping, credentialed browsing, paywall bypass, or personal-data harvesting. The optional local daemon exposes HTTP endpoints for local tooling; keep it bound to trusted local interfaces and do not treat it as a public internet API. Proxy settings, Playwright WebSocket/CDP endpoints, and reused browser sessions can route traffic or cookies through external systems; configure them deliberately. Leave TLS verification enabled unless a specific target has a broken certificate chain and the risk has been accepted.✓Kagi MCP sends search queries, page URLs, filters, date ranges, lens IDs, and extraction requests to the Kagi API. Search and extraction calls can consume Kagi API quota or create API costs, especially when using high limits or inline page extraction. The `kagi_extract` tool fetches public page content as markdown; do not ask it to retrieve private, paywalled, or terms-restricted content unless you have permission. In HTTP mode, clients provide Kagi API keys through bearer tokens; expose the endpoint only behind trusted transport, access controls, and log redaction. The server supports configurable timeouts, retries, and hidden search parameters; tune these before giving broad agent access to current-web workflows.
Privacy notes✓Search queries, fetched URLs, tool parameters, page contents, API keys, and surrounding prompts may be sent to Exa and the MCP client. Research topics can reveal product plans, customers, vulnerabilities, hiring activity, legal matters, or personal interests. Review Exa's current data handling, account, and rate-limit policies before using it with proprietary or regulated workflows.✓Search queries, result URLs, snippets, fetched page text, region codes, SafeSearch settings, prompts, tool arguments, errors, and logs may be visible to the MCP client and model provider. Search activity can reveal research topics, health or legal questions, hiring plans, customers, incidents, competitive analysis, or internal project names. Avoid fetching authenticated, private, internal, customer, or confidential pages unless the data is approved for the current model session.✓Search queries, fetched URLs, result titles, snippets, article content, proxy URLs, browser endpoints, and fetched page text can be exposed to MCP clients, logs, and model context. Live search engines and fetched websites may observe queries, IP address, proxy exit, browser fingerprints, cookies, timing, and request headers. Playwright fallback or CDP reuse can expose browser state, existing cookies, logged-in sessions, or verification state to fetched pages. The project includes public URL validation and private-network target protections, but operators should still avoid fetching internal, secret, or customer-specific URLs. Redact sensitive search terms and downloaded page content before sharing transcripts or logs.✓Kagi receives search queries, requested URLs, search filters, result domains, lens IDs, extraction targets, API keys, and request metadata. MCP clients and logs may store user questions, result snippets, extracted markdown, trace IDs, and error bodies returned by the Kagi API. Hosted HTTP deployments can process keys for multiple users; avoid server, proxy, and platform logs that record `Authorization` headers. Extracted pages may include personal data, copyrighted text, internal URLs, or sensitive context if the user provides those URLs.
Prerequisites
  • MCP client with hosted or remote MCP support, or mcp-remote for clients that need a stdio bridge.
  • Exa API key for higher limits, production usage, or npm-package configuration.
  • Network access to the Exa hosted MCP endpoint and target webpages.
  • Python 3.10 or newer available to the MCP client runtime.
  • uvx available for package execution.
  • Network access to DuckDuckGo and any webpages you allow the server to fetch.
  • Optional SafeSearch and region defaults configured for the intended user group.
  • Node.js 18 or newer for the published npm package.
  • Review of search-engine terms, scraping limits, rate limits, and allowed use for the target websites.
  • Optional proxy configuration only when live search or fetch traffic must route through an approved proxy.
  • Optional Playwright or browser endpoint setup only when request-based search/fetch is insufficient.
  • Python 3.12 and uv for the recommended `uvx kagimcp` install path.
  • A Kagi API key stored in `KAGI_API_KEY` for local stdio use.
  • Review of Kagi API billing, rate limits, search workflows, extraction behavior, and any client logs that may capture query text.
  • Optional HTTP deployment review if exposing the streamable HTTP transport to multiple users.
Install
npx -y mcp-remote https://mcp.exa.ai/mcp
uvx duckduckgo-mcp-server
npx -y open-websearch@latest
uvx kagimcp
Config
{
  "mcpServers": {
    "exa": {
      "url": "https://mcp.exa.ai/mcp"
    }
  }
}
{
  "mcpServers": {
    "ddg-search": {
      "command": "uvx",
      "args": ["duckduckgo-mcp-server"]
    }
  }
}
{
  "mcpServers": {
    "open-websearch": {
      "command": "npx",
      "args": [
        "-y",
        "open-websearch@latest"
      ],
      "env": {
        "MODE": "stdio",
        "DEFAULT_SEARCH_ENGINE": "duckduckgo",
        "ALLOWED_SEARCH_ENGINES": "duckduckgo,startpage,bing",
        "NPM_CONFIG_IGNORE_SCRIPTS": "true"
      },
      "type": "stdio"
    }
  }
}
Manual-only setup:
uvx kagimcp
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed
Open 4 picks in the interactive comparison tool

Related guides

Source-backed guides for putting this to work.

Chrome Integration for Web App Debugging With Claude Code

Debug web apps with Claude in Chrome and Claude Code together.

Added 1mo ago
guidesReview firstSource-backedReview first
Safety ✓ Privacy ✓by kiannidev

Claude Code On The Web For Repository Planning

Plan repository work with Claude Code on the web before local implementation.

Added 1mo ago
guidesReview firstSource-backedReview first
Safety ✓ Privacy ✓by kiannidev

Remote MCP Server Security Review Checklist

Review remote MCP servers for OAuth, transport, and tool scope before team rollout.

Added 1mo ago
guidesReview firstSource-backedReview first
Safety ✓ Privacy ✓by kiannidev

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.