Solodit MCP Server
OfficialClick on "Install 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., "@Solodit MCP Serversearch for critical severity findings in DeFi protocols"
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.
Solodit MCP Server
A Model Context Protocol (MCP) server that provides access to Cyfrin Solodit, the world's largest database of smart contract security findings and vulnerabilities.
Features
Search 49,000+ Security Findings: Access comprehensive smart contract audit findings from major firms
Advanced Filtering: Filter by impact, audit firms, tags, protocols, languages, and more
Quality Metrics: Search by quality and rarity scores
Rate Limited API: Respects Solodit's rate limits (20 requests per 60 seconds)
Universal MCP Support: Works with Claude Desktop, Claude Code, Cursor, VS Code with GitHub Copilot, and any MCP-compatible client
Related MCP server: stepsecurity-mcp
Prerequisites
Node.js 18 or higher
A Solodit API key (get one from Cyfrin Solodit)
Installation
Recommended: Global Installation
Install the package globally to use it from anywhere:
# Clone or download this repository
cd solodit-mcp
# Install dependencies and build
npm install
npm run build
# Install globally (creates the 'solodit-mcp' command)
npm install -g .After global installation, the solodit-mcp command will be available system-wide.
Alternative: Local Development
For development or if you prefer not to install globally:
cd solodit-mcp
npm install
npm run buildThen use the full path to dist/index.js in your configuration.
Configuration
1. Get Your API Key
Visit Cyfrin Solodit and obtain your API key.
2. Configure for Your MCP Client
Choose your preferred client below:
Edit the Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
If installed globally (recommended):
{
"mcpServers": {
"solodit": {
"command": "solodit-mcp",
"env": {
"SOLODIT_API_KEY": "sk_your_api_key_here"
}
}
}
}If using local installation:
{
"mcpServers": {
"solodit": {
"command": "node",
"args": ["/ABSOLUTE/PATH/TO/solodit-mcp/dist/index.js"],
"env": {
"SOLODIT_API_KEY": "sk_your_api_key_here"
}
}
}
}After saving, restart Claude Desktop.
Claude Code automatically discovers MCP servers configured in your settings.
Create or edit ~/.config/claude-code/settings.json:
If installed globally (recommended):
{
"mcpServers": {
"solodit": {
"command": "solodit-mcp",
"env": {
"SOLODIT_API_KEY": "sk_your_api_key_here"
}
}
}
}If using local installation:
{
"mcpServers": {
"solodit": {
"command": "node",
"args": ["/ABSOLUTE/PATH/TO/solodit-mcp/dist/index.js"],
"env": {
"SOLODIT_API_KEY": "sk_your_api_key_here"
}
}
}
}Or use environment variables:
export SOLODIT_API_KEY=sk_your_api_key_here
claude-codeCursor supports MCP through its settings configuration.
Edit the Cursor config file:
macOS: ~/Library/Application Support/Cursor/User/settings.json
Windows: %APPDATA%\Cursor\User\settings.json
Linux: ~/.config/Cursor/User/settings.json
If installed globally (recommended):
{
"mcpServers": {
"solodit": {
"command": "solodit-mcp",
"env": {
"SOLODIT_API_KEY": "sk_your_api_key_here"
}
}
}
}If using local installation:
{
"mcpServers": {
"solodit": {
"command": "node",
"args": ["/ABSOLUTE/PATH/TO/solodit-mcp/dist/index.js"],
"env": {
"SOLODIT_API_KEY": "sk_your_api_key_here"
}
}
}
}Restart Cursor after making changes.
VS Code supports MCP servers through the GitHub Copilot extension (requires Copilot Chat).
Edit your VS Code settings:
macOS: ~/Library/Application Support/Code/User/settings.json
Windows: %APPDATA%\Code\User\settings.json
Linux: ~/.config/Code/User/settings.json
If installed globally (recommended):
{
"github.copilot.chat.mcp.servers": {
"solodit": {
"command": "solodit-mcp",
"env": {
"SOLODIT_API_KEY": "sk_your_api_key_here"
}
}
}
}If using local installation:
{
"github.copilot.chat.mcp.servers": {
"solodit": {
"command": "node",
"args": ["/ABSOLUTE/PATH/TO/solodit-mcp/dist/index.js"],
"env": {
"SOLODIT_API_KEY": "sk_your_api_key_here"
}
}
}
}Alternatively, use the VS Code Command Palette:
Press
Cmd+Shift+P(macOS) orCtrl+Shift+P(Windows/Linux)Type "Preferences: Open User Settings (JSON)"
Add the configuration above
Reload VS Code after configuration.
Note: MCP support in VS Code requires GitHub Copilot Chat extension v0.12.0 or later.
For other MCP-compatible clients:
If installed globally:
{
"command": "solodit-mcp",
"env": {
"SOLODIT_API_KEY": "sk_your_api_key_here"
}
}If using local installation:
{
"command": "node",
"args": ["/ABSOLUTE/PATH/TO/solodit-mcp/dist/index.js"],
"env": {
"SOLODIT_API_KEY": "sk_your_api_key_here"
}
}Available Tools
1. search_findings
Search Solodit for smart contract security findings with advanced filtering options.
Parameters:
keywords(string): Search keywords to find in title and contentimpact(array): Filter by severity -["HIGH", "MEDIUM", "LOW", "GAS"]firms(array): Filter by audit firm names (e.g.,["Cyfrin", "Sherlock", "Code4rena"])tags(array): Filter by vulnerability tags (e.g.,["Reentrancy", "Oracle", "Access Control"])protocol(string): Filter by protocol name (partial match)protocolCategory(array): Filter by protocol categories (e.g.,["DeFi", "NFT", "Lending"])languages(array): Filter by programming languages (e.g.,["Solidity", "Rust", "Cairo"])user(string): Filter by finder/auditor handle (partial match)minFinders(string): Minimum number of findersmaxFinders(string): Maximum number of findersreportedDays(string): Time period -"30","60","90", or"alltime"qualityScore(number): Minimum quality score (0-5)rarityScore(number): Minimum rarity score (0-5)sortField(string): Sort by"Recency","Quality", or"Rarity"sortDirection(string):"Desc"or"Asc"page(number): Page number (default: 1)pageSize(number): Results per page (default: 20, max: 100)
Example Usage:
Search for high severity reentrancy vulnerabilities:
- keywords: "reentrancy"
- impact: ["HIGH"]
- sortField: "Quality"
- pageSize: 102. get_finding_by_id
Get detailed information about a specific finding by its ID or slug.
Parameters:
keywords(string, required): The finding ID or slug to search for
Example Usage:
Get finding details by ID:
- keywords: "finding-id-12345"Usage Examples
Example 1: Search for High Severity Findings
Use the search_findings tool with:
- impact: ["HIGH"]
- pageSize: 20
- sortField: "Recency"Example 2: Find Oracle-Related Issues in DeFi
Use the search_findings tool with:
- tags: ["Oracle"]
- protocolCategory: ["DeFi"]
- qualityScore: 3Example 3: Search Specific Audit Firm Reports
Use the search_findings tool with:
- firms: ["Cyfrin", "Trail of Bits"]
- impact: ["HIGH", "MEDIUM"]
- reportedDays: "30"Example 4: Search by Keywords
Use the search_findings tool with:
- keywords: "flash loan attack"
- sortField: "Quality"
- sortDirection: "Desc"Development
Run in Development Mode
npm run devBuild
npm run buildWatch Mode
npm run watchRate Limiting
The Solodit API has a default rate limit of 20 requests per 60-second window. The server includes rate limit information in responses:
Total requests allowed
Remaining requests in current window
Time when the window resets
If you exceed the rate limit, you'll receive a 429 Too Many Requests error.
Error Handling
The server provides clear error messages for common issues:
Missing API Key: "SOLODIT_API_KEY environment variable is not set"
Invalid API Key: "Solodit API error (401): Invalid API key"
Rate Limit Exceeded: "Solodit API error (429): Rate limit exceeded"
Network Errors: Connection and timeout errors are properly reported
Available Filters Reference
Popular Audit Firms
Cyfrin
Sherlock
Code4rena
Trail of Bits
OpenZeppelin
Consensys Diligence
Pashov Audit Group
Spearbit
Hacken
Chainsecurity
Common Vulnerability Tags
Reentrancy
Oracle
Access Control
Integer Overflow/Underflow
Front-running
Logic Error
DOS
Price Manipulation
Flash Loan
Griefing
Protocol Categories
DeFi
NFT
Lending
DEX
Staking
Governance
Bridge
Options Vault
Yield Aggregator
Programming Languages
Solidity
Rust
Cairo
Vyper
Move
For a comprehensive list of all available filter values, see the Solodit API Documentation.
Project Structure
solodit-mcp/
├── src/
│ └── index.ts # Main MCP server implementation
├── dist/ # Compiled JavaScript (generated)
├── package.json
├── tsconfig.json
├── README.md
└── .env.exampleTroubleshooting
API Key Issues
If you get authentication errors:
Verify your API key is correct
Ensure the environment variable is set properly
Restart your MCP client after configuration changes
Connection Issues
If the server fails to connect:
Check your internet connection
Verify the Solodit API is accessible:
curl https://solodit.cyfrin.ioCheck for any firewall or proxy issues
Server Not Showing Up
If the MCP server doesn't appear in your client:
Verify the path to
dist/index.jsis absolute, not relativeCheck that the build completed successfully (
npm run build)Ensure the config file JSON syntax is valid
Restart your MCP client completely
Check client logs for error messages
Rate Limit Issues
If you're hitting rate limits:
Reduce the frequency of requests
Implement delays between searches
Use pagination wisely (larger page sizes for fewer requests)
Contributing
Contributions are welcome! Please feel free to submit issues and pull requests.
License
MIT
Resources
Support
For issues related to:
This MCP Server: Open an issue in this repository
Solodit API: Contact Cyfrin Support
MCP Protocol: See MCP Documentation
Available Tools
2 toolsget_finding_by_idB
Get detailed information about a specific finding by its ID or slug
| Name | Required | Description | Default |
|---|---|---|---|
| keywords | Yes | The finding ID or slug to search for |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It only says 'Get detailed information' without specifying what 'detailed' includes, whether the operation is read-only, how errors are handled (e.g., not found), or any other behavioral context. This leaves significant room for ambiguity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that is front-loaded with the action and target. Every word is relevant and there is no redundant or filler content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple lookup tool with one parameter, the description is adequate but incomplete. It does not describe the return format or the degree of detail, and without an output schema, this information is missing. The differentiation from sibling 'search_findings' is only implicit, so there is room for more contextual guidance.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The parameter description ('The finding ID or slug to search for') matches the tool description and already exists in the schema. Since schema description coverage is 100%, the description does not add additional meaning or clarify parameter formats beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function with a specific verb ('Get') and resource ('finding by its ID or slug'). It distinguishes this tool from the sibling 'search_findings' by focusing on retrieving a single, specific finding rather than performing a search.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives no explicit guidance about when to use this tool instead of 'search_findings'. It implies usage for looking up a known finding by ID/slug, but does not mention exclusions or alternatives, so the agent is left to infer the appropriate context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_findingsB
Search Solodit for smart contract security findings and vulnerabilities. You can filter by keywords, impact level, audit firms, tags, protocols, and more.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Page number (default: 1) | |
| tags | No | Filter by vulnerability tags (e.g., Reentrancy, Oracle, Access Control) | |
| user | No | Filter by finder/auditor handle (partial match) | |
| firms | No | Filter by audit firm names (e.g., Cyfrin, Sherlock, Code4rena) | |
| impact | No | Filter by impact level (severity) | |
| keywords | No | Search keywords to find in title and content | |
| pageSize | No | Results per page (default: 20, max: 100) | |
| protocol | No | Filter by protocol name (partial match) | |
| languages | No | Filter by programming languages (e.g., Solidity, Rust, Cairo) | |
| sortField | No | Sort by field (default: Recency) | |
| maxFinders | No | Maximum number of finders | |
| minFinders | No | Minimum number of finders | |
| rarityScore | No | Minimum rarity score (0-5) | |
| qualityScore | No | Minimum quality score (0-5) | |
| reportedDays | No | Filter by time period (30, 60, 90 days, or alltime) | |
| sortDirection | No | Sort direction (default: Desc) | |
| protocolCategory | No | Filter by protocol categories (e.g., DeFi, NFT, Lending) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states that it searches and filters, without mentioning return format, pagination behavior, sorting defaults, authentication needs, or how filters combine. The schema documents parameters, but the description adds little beyond the verb and resource.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences long, front-loads the core purpose, and contains no filler or redundant information. Every word contributes meaning.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 17 optional parameters and no output schema, the description is under-specified. It does not explain what the returned findings look like, how multiple filters interact, or what the default sorting and pagination behavior is. The description says 'and more' without elaboration, leaving critical context missing for a complex search tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description mentions filters for keywords, impact, firms, tags, and protocols, which maps to several parameters, but it adds no additional semantic detail beyond what the schema already provides. The phrase 'and more' is vague.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches Solodit for smart contract security findings and vulnerabilities, using a specific verb and resource. It distinguishes itself from the sibling get_finding_by_id by being a search/filter tool rather than a direct lookup.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for searching and filtering findings but provides no explicit guidance on when to prefer this over get_finding_by_id or when not to use it. No alternatives are mentioned, leaving usage context implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
2 tool updates
v1.0.0- First observed
get_finding_by_id - First observed
search_findings
TDQS
The two tools have clearly distinct purposes: one searches across findings with filters, the other retrieves a specific finding by ID. There is no overlap or ambiguity.
Both tool names follow the same verb_noun pattern using snake_case: search_findings and get_finding_by_id. This is consistent and predictable.
With only two tools, the set feels minimal but reasonable for a focused read-only API. The scope is narrow, yet two tools could be seen as slightly thin; however, they cover the core needs.
The tool surface covers the essential operations for accessing Solodit findings: searching and retrieving by ID. Minor gaps exist, such as no explicit listing endpoint, but search with filters effectively fills that role.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
Capability registry for the agentic economy. Semantic search over verified MCP server listings.
Crypto market intelligence, token rug-checks, and wallet verification in one MCP server.
The OpenZeppelin Solidity Contracts MCP server integrates OpenZeppelin's security and style rules into AI-driven development workflows, enabling AI assistants to generate safe, correct, and production-ready smart contracts. It automatically validates generated code against OpenZeppelin standards (including imports, modifiers, naming conventions, and security checks) and supports various contract types including ERC-20, ERC-721, ERC-1155, Stablecoins, RWA, Governor, and Account contracts through prompt-driven workflows.
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceA server that allows searching and retrieving Solodit vulnerability reports through Model Context Protocol (MCP).2942ISC

stepsecurity-mcpofficial
AlicenseAqualityDmaintenanceMCP server for the StepSecurity platform that enables investigating supply-chain and CI/CD security issues through natural language.30294Apache 2.0- AlicenseAqualityDmaintenanceEnables searching over 20,000+ smart contract audit findings from Solodit, with filters for severity, firm, tags, and more. Designed for use with AI coding agents like Claude Code and Codex CLI.432157MIT
- FlicenseNot gradedqualityCmaintenanceAn MCP server that statically audits Solidity smart contracts for common vulnerabilities like reentrancy and access control, enabling developers to identify and fix security issues via natural language.-
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/zerotrust-labs/solodit-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server