1. Conduid
  2. Agents
  3. Shield
MCP server · Agents

Shield

Semantic LLM firewall for the Model Context Protocol. A local proxy that classifies every untrusted tool result, tool description and server request with an 86M encoder, pins tool manifests, tracks session taint, and blocks indirect prompt injection before it reaches your agent. Runs offline for $0. Apache-2.0. Design phase.

34Low

Scored 2 hours ago · breakdown

About Shield

Shield is an MCP server published by rishikeshvarma in the Agents category: semantic LLM firewall for the Model Context Protocol. A local proxy that classifies every untrusted tool result, tool description and server request with an 86M encoder, pins tool manifests, tracks session taint, and blocks indirect prompt injection before it reaches your agent. Runs offline for $0. Apache-2.0. Design phase.

The repository has 1 stars and 0 forks, with the last commit 23 days ago. Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/rishikeshvarma/MCP-Shield

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Shield

Powered by Claude · Grounded in docs

I know everything about Shield. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Questions

About Shield

How do I install Shield?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Shield safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Shield still maintained?

Yes — the last commit was 23 days ago. The repository has 1 stars and 0 forks.