Atlas / MCP servers / marchev / Claudit

ClauditSAFE

mcp/marchev/claudit

MCP server for searching Solodit smart contract security findings

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
4 4r · 0w · 0d
Transport
stdio
License
MIT
Stars
158
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Smart contract security findings for AI coding agents

Search Solodit's 20,000+ audit findings from Claude Code and Codex CLI.

[](https://www.npmjs.com/package/@marchev/claudit) [](LICENSE) [](package.json) [](https://giveth.io/project/claudit-0)

Quick Start · Tools · Examples · Configuration

Quick Start

curl -fsSL https://raw.githubusercontent.com/marchev/claudit/main/install.sh | sh

The 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 Sherlock

Manual install

Claude 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.md

Codex CLI

codex mcp add solodit \
--env SOLODIT_API_KEY=sk_your_key_here \
-- npx -y @marchev/claudit@latest

Tools

search_findings

Search across all findings with filters.

Read from source at commit 826891db5274OBSERVED · 2026-10-07
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code
claude mcp add claudit --env SOLODIT_API_KEY=${SOLODIT_API_KEY} -- npx -y @marchev/[email protected]
claude-desktop
{
  "mcpServers": {
    "claudit": {
      "command": "npx",
      "args": [
        "-y",
        "@marchev/[email protected]"
      ],
      "env": {
        "SOLODIT_API_KEY": "${SOLODIT_API_KEY}"
      }
    }
  }
}
03

Exposed tools (4)

4 read · 0 write · 0 destructive.

ToolRiskDescription
get_claudit_versionreadReturns the currently running version of the Claudit MCP server.
get_filter_optionsreadList available filter values for Solodit search (firms, tags, categories, languages). Use this to discover valid values for search_findings filters.
get_findingreadGet full details for a specific Solodit finding by its numeric ID (preferred), URL, or slug. Returns complete markdown content and all metadata.
search_findingsreadSearch Solodit
04

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.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
declared (3 observation(s))
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (2)

LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@modelcontextprotocol/sdk, zod, @types/node, typescript
Why it matters. 4 dependency range(s) float
Fix. pin exact versions or ship a lockfile
INFOSupply chain · prompt.pipe_to_shell · CWE-829, CWE-1357
README.md:29
curl -fsSL https://raw.githubusercontent.com/marchev/claudit/main/install.sh | sh

Gates applied: no_behavioural_pass.

Audited 2026-10-07 · audit v0.4.1 · source sha 826891db5274full audit observations/trust-audit/mcp-server/marchev__claudit.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-07826891db5274SAFEB89first audit
06

Questions

What is the Claudit MCP server?

MCP server for searching Solodit smart contract security findings

What tools does Claudit expose?

4 in total: 4 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Claudit safe to connect to an agent?

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 server reads B.

What credentials does Claudit need?

It reads SOLODIT_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does Claudit run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as @marchev/claudit at 0.1.19.

How current is this page?

The grade is for one exact copy of the source (826891db5274), read on 2026-10-07. The repository is watched and re-audited when it changes.

Advertisement