by poly-mcp · MCP Server · ★ 170
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Polymcp provides a simple and efficient way to interact with MCP servers using custom agents
| Stars | 170 |
| Forks | 14 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 57.4970902558995/100 |
| Open Issues | 1 |
| Last Updated | 2026-04-30 |
| Created | 2025-10-10 |
| Platforms | cli, mcp, node |
| Est. Tokens | ~91k |
Looking for a PolyMCP alternative? If you're comparing PolyMCP with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools,
MCP Fusion - The framework for AI-native MCP servers.
Agent samples built using the Strands Agents SDK.
A minimalistic MCP client with a good feature set.
Ultimate Context Engineering Infrastructure, starting from MCPs and Integrations
Codebase intelligence for AI. Detects patterns & conventions + remembers decisions across sessions. MCP server
Explore other popular mcp server tools:
PolyMCP is Polymcp provides a simple and efficient way to interact with MCP servers using custom agents. It is categorized as a MCP Server with 170 GitHub stars.
PolyMCP is primarily written in TypeScript. It covers topics such as agent-framework, ai-agent, anthropic.
You can find installation instructions and usage details in the PolyMCP GitHub repository at github.com/poly-mcp/PolyMCP. The project has 170 stars and 14 forks, indicating an active community.
PolyMCP is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to PolyMCP on Agent Skills Hub include mcp-client-for-ollama, mcp-fusion, samples. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: