Exa MCP Server connects AI agents to Exa, a service for searching the web, fetching webpage content, and carrying out multi-step research. MCP, or Model Context Protocol, lets compatible AI clients call these capabilities as tools. The catalogue skills, MCP server, and plugin provide ways for coding agents to use Exa for web research.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add exa-labs/exa-mcp-server --skill searchgit clone --depth 1 https://github.com/exa-labs/exa-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/exa-labs/exa-mcp-server/search)<a href="https://agentmods.dev/skills/exa-labs/exa-mcp-server/search"><img src="https://agentmods.dev/badge/skills/exa-labs/exa-mcp-server/search.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 169 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.03170 |
| Opus 5 | $0.00028 | $0.01585 |
| Sonnet 5 | $0.00011 | $0.00634 |
| Haiku 4.5 | $0.00006 | $0.00317 |
Grade A, and why
search scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
2 near-identical copies found in the catalogue:
- search — 100% identical, 0 lines differ
- exa-search — 95% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exa Research Orchestrator
You are the orchestrator. Your job: understand the query, plan the work, dispatch subagents with the right context, then compile and deliver the final result.
Prerequisites: Auth
Server: https://mcp.exa.ai/mcp.
- OAuth (recommended) — client opens
auth.exa.ai, user signs in with Google / SSO / email, JWT is attached automatically. No key to copy. - API key — if OAuth isn't available, get one at https://dashboard.exa.ai/api-keys and pass it via
Authorization: Bearer …,?exaApiKey=…, orEXA_API_KEY(local npm). - Anonymous — works without setup but rate-limited.
On auth / rate-limit errors, surface the fix (prefer OAuth) — don't fall back to generic web search.
Date Calculation (Do This First)
If the query involves time ("last week", "recent", "past 6 months"), calculate exact dates from today's date in your environment context. Write out the calculation explicitly before doing anything else. Never eyeball dates or reuse dates from examples.
Step 1: Assess the Query
Read the user's query and determine two things:
How complex is this?
- Extremely Simple (e.g. reading the contents of 1-2 pages): Handle it yourself. Read
references/searching.mdfor query-writing guidance, run the searches, review and filter results, then respond directly. No subagents needed. - Moderate (when a fast or low-effort search is requested): Delegate to 1 subagent to keep your context window clean.
- Advanced (clear topic, clear filters, a few parallel searches): Light subagent use. One round of parallel subagents, then compile.
- Complex (cross-referencing across entity types, multi-hop chains, exhaustive coverage, semantic filtering): Full multi-pass with parallel subagents.
Confirm when ambiguous: If the query could reasonably be handled as Extremely Simple/Moderate OR as Advanced/Complex, pause and ask the user before proceeding. Present:
- Your interpretation of the query
- The two (or more) plausible complexity levels
- What each level would look like in practice (e.g., "I can do a quick 1-2 search lookup, or I can fan out across 3-4 subagents to get deeper coverage")
- Let the user choose
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/extraction.md 3.0 KB
- references/filtering.md 2.2 KB
- references/patterns-code.md 557 B
- references/patterns-companies.md 1004 B
- references/patterns-news.md 481 B
- references/patterns-papers.md 746 B
- references/patterns-people.md 1.4 KB
- references/patterns-relationships.md 1.4 KB
- references/searching.md 4.9 KB
- references/source-quality.md 2.2 KB
- references/synthesis.md 2.2 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 208 lines · 55 tokens per session scan A 0aacd119c70b
search is a skill published in the GitHub repository exa-labs/exa-mcp-server (4,987 stars, last pushed 18d ago), licensed MIT. It adds 55 tokens to every session and 3,170 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
opengrok
Use this skill whenever the user wants to search, navigate, or understand source code in a large codebase — even when they don't say "OpenGrok". Trigger for: finding where a function or class is defined, tracking where something is called or referenced, reading a remote source file, checking who last changed a line…
opengrok-cpp
Specialized patterns for navigating C++ codebases with OpenGrok MCP.
opengrok-investigation
Use this skill when conducting a structured investigation into a bug, unknown module, or impact analysis using OpenGrok. Provides step-by-step methodology for systematic codebase investigation with memory-backed state management. Trigger when: diagnosing a bug with unknown root cause, exploring an unfamiliar module…
opengrok-session
Session lifecycle management for OpenGrok MCP investigations. Use this skill to understand how to start, maintain, and complete an OpenGrok session with proper memory bank state management. Trigger at session start when you know an investigation will span multiple turns, or when restoring a prior session.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
cortex-explore-memory
Explore the memory system's state, find gaps in knowledge, assess coverage, and get diagnostic information. Use when the user asks 'what does my memory look like', 'show me memory stats', 'what am I missing', 'how good is my knowledge', 'memory health', 'show coverage', 'find gaps', 'what topics are weak', or when you…