claudit
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@claudit Search Solodit for oracle manipulation HIGH severity findings"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
claudit
Smart contract security findings for AI coding agents
Search Solodit's 20,000+ audit findings from Claude Code and Codex CLI.
Quick Start · Tools · Examples · Configuration
Quick Start
curl -fsSL https://raw.githubusercontent.com/marchev/claudit/main/install.sh | shThe installer detects Claude Code and/or Codex CLI, prompts for your Solodit API key, and registers the MCP server.
Then just ask:
> Find 5 solo findings by 0x52 at SherlockClaude Code
claude mcp add --scope user --transport stdio solodit \
--env SOLODIT_API_KEY=sk_your_key_here \
-- npx -y @marchev/claudit@latest
# (Optional) Install companion skill
mkdir -p ~/.claude/skills/solodit
curl -fsSL https://raw.githubusercontent.com/marchev/claudit/main/.claude/skills/solodit/SKILL.md \
-o ~/.claude/skills/solodit/SKILL.mdCodex CLI
codex mcp add solodit \
--env SOLODIT_API_KEY=sk_your_key_here \
-- npx -y @marchev/claudit@latestRelated MCP server: solidit-mcp-server
Tools
search_findings
Search across all findings with filters.
Parameter | Type | Description |
|
| Text search in title and content |
|
|
|
|
| Audit firm names |
|
| Vulnerability tags |
|
| Programming language |
|
| Protocol name (partial match) |
|
|
|
|
|
|
|
|
|
|
| Page number (default 1) |
|
| Results per page (default 10, max 100) |
|
| See below |
Field | Type | Description |
|
| Minimum quality score (0-5) |
|
| Minimum rarity score (0-5) |
|
| Finder/auditor handle |
|
| Minimum number of finders |
|
| Maximum number of finders |
|
| ISO date string |
|
| Protocol categories |
|
| Forked protocol names |
get_finding
Get full details for a specific finding by numeric ID, Solodit URL, or slug.
get_filter_options
List all valid filter values — firms, tags, categories, languages — with finding counts.
Examples
Search Solodit for oracle manipulation HIGH severity findings
Find all Sherlock findings about flash loans
What reentrancy issues exist in lending protocols?
Show me solo findings by 0x52
Get recent HIGH severity Solidity findings sorted by qualityConfiguration
Claude Code:
claude mcp remove solodit
claude mcp add --scope user --transport stdio solodit \
--env SOLODIT_API_KEY=sk_new_key \
-- npx -y @marchev/claudit@latestCodex CLI:
codex mcp remove solodit
codex mcp add solodit \
--env SOLODIT_API_KEY=sk_new_key \
-- npx -y @marchev/claudit@latestCursor MCP
{
"mcpServers": {
"solodit": {
"command": "npx",
"args": ["-y", "@marchev/claudit@latest"],
"env": {
"SOLODIT_API_KEY": "sk_new_key"
}
}
}
}Claude Code:
claude mcp remove solodit
rm -rf ~/.claude/skills/soloditCodex CLI:
codex mcp remove soloditgit clone https://github.com/marchev/claudit.git
cd claudit
npm install
npm run build
# Test locally
SOLODIT_API_KEY=sk_your_key node dist/index.jsSupport
Claudit is a solo-maintained public good for Ethereum security. If it saves you time or finds bugs for you, consider supporting its continued development on Giveth:
MIT License
Available Tools
4 toolsget_claudit_versionA
Returns the currently running version of the Claudit MCP server.
Inputs: no named parameters.
get_filter_optionsA
List available filter values for Solodit search (firms, tags, categories, languages). Use this to discover valid values for search_findings filters.
Inputs: no named parameters.
get_findingA
Get full details for a specific Solodit finding by its numeric ID (preferred), URL, or slug. Returns complete markdown content and all metadata.
Inputs: identifier (required).
search_findingsA
Search Solodit's 20k+ smart contract security findings from real audits. Returns severity, firm, protocol, tags, quality score, content snippet, and Solodit URL for each finding. IMPORTANT: Each result includes a Solodit URL — always include it when presenting results to the user.
Inputs: page, tags, firms, sort_by, +8 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool targets a distinct action: version retrieval, filter discovery, single finding detail, and finding search. There is no overlap in purpose.
All tools use snake_case with a verb_noun pattern. Three use 'get_' and one uses 'search_', but the verb clearly indicates the operation type, and the naming is predictable.
With 4 tools, the server is well-scoped for its purpose of searching and retrieving audit findings, plus supporting utilities like version and filter options.
The server provides a complete surface for read-only access to findings: discover filters, search, and get full details. No missing operations for its intended use case.
Related MCP Connectors
Solidity vulnerability scan (Slither) for AI agents. Free preview; full report 1 USDC on Solana x402
Search and audit NIST NVD CVEs by keyword, severity, CWE, CISA KEV status, and CPE.
Code intelligence for coding agents: semantic, AST, graph, and full-text search. 279+ languages.
AI security scanner for Solidity + free CC0 dataset of Sherlock audit-competition acceptance rates.
Related MCP Servers
AlicenseAqualityDmaintenanceMCP server that provides access to Cyfrin Solodit's database of smart contract security findings, enabling search and filtering by impact, firms, tags, and more.21MIT- AlicenseAqualityDmaintenanceConnects AI assistants to Solodit's 49,000+ blockchain vulnerability database, enabling search, browse, and lookup of audit findings directly from your AI workflow.4MIT
- AlicenseBqualityDmaintenanceEnables read-only search over a curated, provenance-preserving corpus of EVM smart-contract security knowledge, providing tools for retrieving audit findings, document context, and source information.5MIT
- AlicenseCqualityCmaintenanceEnables AI agents and security researchers to query a curated knowledge base of 1,032 verified smart contract vulnerability findings from Sherlock audit contests, including acceptance rates and examples per vulnerability pattern.359 npm2MIT