Mcp Exa SearchSAFE
High-performance AI coding agent CLI written in Rust with zero unsafe code
Overview
High-performance AI coding agent CLI written in Rust with zero unsafe code
46a2537504c9OBSERVED · 2026-10-10What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
---
name: mcp-exa-search
description: Search the web, research companies, and find code context using Exa AI. Use when performing web searches, company research, or finding programming documentation. Triggers on "search the web", "find online", "research company", "code context for [library]", "Exa search".
---
# Exa AI Search
MCP service at `https://mcp.exa.ai/mcp` (http) with 3 tools.
## Requirements
- `mh` CLI must be installed. If not available, install with:
```bash
curl -fsSL https://raw.githubusercontent.com/vaayne/mcphub/main/scripts/install.sh | sh
```
## Usage
List tools: `mh -u https://mcp.exa.ai/mcp -t http list`
Get tool details: `mh -u https://mcp.exa.ai/mcp -t http inspect <tool-name>`
Invoke tool: `mh -u https://mcp.exa.ai/mcp -t http invoke <tool-name> '{"param": "value"}'`
## Notes
- Run `inspect` before invoking unfamiliar tools to get full parameter schema
- Timeout: 30s default, use `--timeout <seconds>` to adjust
- `getCodeContextExa` is best for programming-related queries (libraries, SDKs, APIs)
## Tools
| Tool | Description |
| -------------------- | ---------------------------------------------------------------------------------------------------------------------------------------- |
| `webSearchExa` | Search the web using Exa AI with real-time results. Supports configurable result counts and returns content from most relevant websites. |
| `companyResearchExa` | Research companies - finds comprehensive info about businesses, operations, news, financials, and industry analysis. |
| `getCodeContextExa` | Search and get relevant context for programming tasks. Best for libraries, SDKs, and API documentation with high quality, fresh context. |
## Examples
```bash
# Web search
mh -u https://mcp.exa.ai/mcp -t http invoke webSearchExa '{"query": "latest AI developments 2024"}'
# Company research
mh -u https://mcp.exa.ai/mcp -t http invoke companyResearchExa '{"company": "OpenAI"}'
# Code context
mh -u https://mcp.exa.ai/mcp -t http invoke getCodeContextExa '{"query": "React hooks best practices"}'
```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 | WARN |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (2)
.beads/beads.jsonl
curl -fsSL https://raw.githubusercontent.com/vaayne/mcphub/main/scripts/install.sh | sh
Gates applied: no_behavioural_pass.
46a2537504c9full audit observations/trust-audit/skill/dicklesworthstone__mcp-exa-search.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-10 | 46a2537504c9 | SAFE | B | 89 | first audit |
Questions
What does the Mcp Exa Search skill do?
High-performance AI coding agent CLI written in Rust with zero unsafe code
Is Mcp Exa Search safe to install?
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 skill reads B.
What can Mcp Exa Search access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (46a2537504c9), read on 2026-10-10. The repository is watched, and a new audit runs when it changes — this is the first audit.