ContextPodsCAUTION
Model Context Protocol management suite/factory. An MCP that can generate and manage other local MCPs in multiple languages. Uses the official SDKs for code gen.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/conorluddy/ContextPods) [](https://opensource.org/licenses/MIT) [](https://turbo.build/) [](docs/METAMCPGUIDE.md) [](https://deepwiki.com/conorluddy/ContextPods) [](https://codecov.io/gh/conorluddy/ContextPods)
The comprehensive MCP development suite with advanced protocol features
Context-Pods is a production-ready development framework for creating, testing, and managing Model Context Protocol (MCP) servers. Built with TypeScript and powered by TurboRepo, it provides everything from basic templates to advanced MCP protocol features including sampling/LLM integration, multi-modal content support, resource subscriptions, and comprehensive testing frameworks.
🚀 Quick Start
# Install and run Context-Pods CLI npx @context-pods/create # Or install globally npm install -g @context-pods/cli context-pods generate # For developers: Use the convenient shell shortcut git clone https://github.com/conorluddy/ContextPods.git cd ContextPods npm install && npm run build ./pods wizard # Interactive setup with all features
✨ Features
🎯 Multiple Language Support
Create MCP servers in your preferred language:
- TypeScript - Full type safety with TurboRepo optimization
- Python - Async support with built-in data science tools
- Rust - High-performance servers with Tokio async runtime
- Shell - Wrap existing CLI tools and scripts as MCP servers
- JavaScript - Simple, no-build-step servers (coming soon)
🤖 Meta-MCP Server
The Meta-MCP Server
8d0ae3b87583OBSERVED · 2026-10-08Connect
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.
claude mcp add testing -- npx -y @context-pods/[email protected]
{
"mcpServers": {
"testing": {
"command": "npx",
"args": [
"-y",
"@context-pods/[email protected]"
]
}
}
}Exposed tools (98)
94 read · 3 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
Configuration | read | Application configuration |
TestClass | read | Test class description |
advanced-ts | read | Advanced TypeScript template |
analysis_type | read | Type of analysis (statistical, trend, correlation) |
analyze-project | read | Comprehensive project analysis including code quality, dependencies, and metrics |
analyze-text | read | Analyze text for metrics, sentiment, and keywords |
analyze-with-llm | read | Analyze content using large language model capabilities |
api-design | read | Help design RESTful APIs with best practices |
architecture-analysis | read | Analyze and provide feedback on software architecture |
authentication | read | Authentication method (jwt, oauth, api-key) |
basic-js | read | Basic JavaScript template |
basic-nodejs | read | Basic Node.js template |
basic-template | read | A basic template |
basic-ts | read | Basic TypeScript template |
calculate | read | Perform mathematical calculations with basic operators |
code | read | The code to review |
code-review | read | Analyze code for quality, bugs, and improvements |
code-review-checklist | read | Comprehensive code review checklist and guidelines |
codeType | read | Type of code (feature, bugfix, refactor) |
complex-wrapper | read | Advanced data processing wrapper |
context | read | Code context where error occurred |
create-content | write | Create multi-modal content from various inputs |
create-file | write | Create a new file with content |
create-mcp | write | Create a new MCP server |
data | read | The data to analyze (JSON, CSV, or description) |
data-analysis | read | Analyze and visualize data patterns |
data-fetcher | read | API data fetching script wrapper |
description | read | Server description |
detail_level | read | Level of detail (basic, detailed, comprehensive) |
documentation | read | Generate comprehensive documentation |
echo | read | Echo the input text |
environment | read | Environment details (OS, runtime version, dependencies) |
error-diagnosis | read | Diagnose and suggest fixes for errors |
error-test | read | Template for testing error handling |
error_message | read | The error message or stack trace |
example-tool | read | An example tool that echoes input |
example_tool | read | An example tool that echoes the input |
focus | read | Specific aspect to focus on (security, performance, style) |
generate | read | Generate server prompt |
generate-code | read | Generate code snippets in various programming languages |
generate-content | read | Generate content using LLM sampling |
generate-server | read | Generate a new MCP server from template |
generate-tests | read | Generate comprehensive test suites for given code |
get-root-info | read | Get detailed information about a specific root |
integration-test-server | read | Server created in integration test |
language | read | Programming language |
list-mcps | read | List all MCP servers |
list-root-directory | read | List contents of a directory within a configured root |
long-description-server | read | A |
my-project | read | Test project description |
my-test-server | read | A test MCP server |
name | read | Server name |
operations | destructive | CRUD operations needed (create, read, update, delete) |
output_format | read | Desired output format (summary, detailed, visual) |
performance-optimization | read | Performance optimization strategies and recommendations |
performance_issues | read | Identified performance issues |
ping | read | Simple ping tool for testing |
pipeline-test-server | read | Test server for pipeline validation |
process-content | read | Process various content types (text, images, audio, etc.) |
process-data | read | Process and transform data |
projectType | read | Type of project |
prompted-name | read | Prompted description |
provided-name | read | Provided description |
python-alt | read | Python template |
python-basic | read | Basic Python MCP server template |
python-only | read | Python only template |
read-file | read | Read the contents of a file |
read_file | read | Reads a file |
refactor-code | read | Intelligently refactor code for better maintainability and performance |
registry-server | read | Test server for registry |
requirements | read | Project requirements |
resource | read | The resource or entity to design API for |
review-code | read | AI-powered code review with suggestions and quality metrics |
serverDescription | read | A brief description of your server |
serverName | read | The name of your MCP server |
style | read | Documentation style (jsdoc, markdown, restructured) |
target_metrics | read | Target performance metrics |
template | read | Template name to use |
template-workflow-server | read | Generated from templates workflow |
test | read | test |
test-completion | read | Test completion suggestions for given context |
test-project | read | User provided description |
test-prompt | read | A test prompt |
test-template | read | Test template |
test-template-with-vars | read | Test template with variables |
test-tool | read | A test tool |
test-wrapper | read | a |
transform-data | read | Transform data using various operations like format, filter, aggregate, sort, or map |
ts-advanced | read | Advanced TypeScript template |
ts-basic | read | Basic TypeScript template |
typescript-advanced | read | Advanced TypeScript MCP server template |
typescript-basic | read | Basic TypeScript MCP server template |
typescript-preferred | read | TypeScript template |
valid-name | read | a |
variable-server | read | Server with variables |
variable-test | read | Template for testing variable substitution |
wrapped-server | read | Wrapped script server |
wrapped-typescript-server | read | Wrapped TypeScript script |
Trust audit
CAUTIONgrade C · trust 79/100 Install with care. The audit found things worth knowing before you trust its output.
| 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 | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- none-observed
- Shell
- declared (5 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (21)
registry.db
operations
.eslintignore
.eslintrc.stricter.json
.lintstagedrc.json
.prettierrc.json
.eslintignore
const hash = crypto.createHash('md5').update(dataString).digest('hex');import type { CommandContext } from '../../src/types/cli-types.js';vi.mock('../../src/utils/output-formatter.js', () => ({vi.mock('../../src/commands/generate.js', () => ({vi.mock('../../src/commands/list.js', () => ({vi.mock('../../src/commands/templates.js', () => ({proxy_pass http://127.0.0.1:3001;
@modelcontextprotocol/sdk, @types/node, @types/tmp, @typescript-eslint/eslint-plugin, @typescript-eslint/parser, @vitest/coverage-v8, eslint, eslint-config-prettier
@context-pods/core, @context-pods/templates, commander, chalk, fs-extra, chokidar, inquirer, ora
zod, @context-pods/templates, typescript, @types/node
@modelcontextprotocol/sdk, @context-pods/core, @context-pods/templates, sqlite3, @types/node, typescript, vitest, eslint
@modelcontextprotocol/sdk, @types/node, typescript
# Add to crontab
Gates applied: no_behavioural_pass, no_license.
8d0ae3b87583full audit observations/trust-audit/mcp-server/conorluddy__contextpods.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 8d0ae3b87583 | CAUTION | C | 79 | first audit |
Questions
What is the ContextPods MCP server?
Model Context Protocol management suite/factory. An MCP that can generate and manage other local MCPs in multiple languages. Uses the official SDKs for code gen.
What tools does ContextPods expose?
98 in total: 94 read-only, 3 that write, and 1 that can delete or overwrite (operations). Every one is listed on this page with its risk.
Is ContextPods safe to connect to an agent?
With care. The audit graded it C (79/100) and found 21 things worth knowing before you trust this server, listed below with the exact line each was found on. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does ContextPods need?
No credential environment variables were found in its source, so it appears to need none.
How does ContextPods run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @context-pods/testing at 0.2.0.
How current is this page?
The grade is for one exact copy of the source (8d0ae3b87583), read on 2026-10-08. The repository is watched and re-audited when it changes.