Knowledge · MCP Server
Securing the Context7 MCP server
The Context7 MCP server gives an agent library documentation lookup for coding agents. That is useful, and it is also a set of real capabilities pointed at a real system. Here is what it exposes, why it is worth governing, and the policy to put in front of it.
What the server hands your agent
Fetching up-to-date documentation and code snippets for third-party libraries into the agent context.
Why it is worth governing
- Documentation is remote content the agent treats as authoritative, which is exactly the property an injected instruction needs.
- Returned code snippets are frequently pasted into a project with little review.
- A docs lookup looks harmless, so it rarely gets policy attention - which is why it belongs in the untrusted tier.
Tag what the tools actually do
Prismor tags every tool by behavior rather than by name, so rules survive a server adding tools you have never seen. A sensible starting map for Context7:
| Tool pattern | Tags | Why |
|---|---|---|
| mcp__context7__* | untrusted_content | all returned content is remote and unverified |
Patterns are illustrative globs. Run prismor tags list to see how your installed tools actually resolve.
The policy
Rules read as a sentence: a tag, then or with another tag, and what to do about it. Note the mode - start by watching, not blocking.
settings:
tool_tags:
enabled: true
mode: observe # switch to enforce once the log looks right
tags:
"mcp__context7__*": [untrusted_content]
rules:
- "untrusted_content then critical_action -> block"Putting Context7 behind the gateway
You do not change the Context7 server or how it is configured. Move your existing mcpServers block behind the Prismor gateway and point your agent at Prismor instead:
prismor mcp-gateway install # moves your .mcp.json servers behind the gateway
prismor mcp-gateway uninstall # restores the original, backup keptYour agent sees the same Context7 tools, namespaced as mcp__context7__<tool>. Every call is evaluated against policy before it is forwarded, and every result is scanned as untrusted content before the model sees it.
Frequently asked questions
Is the Context7 MCP server safe to give an AI agent?
It is as safe as the credential behind it and the policy in front of it. The server itself is not the problem: the risk is that an agent can combine Context7 access with everything else in the session, with no record of what it did. Front it with a gateway that evaluates each call and logs the verdict.
Does Prismor replace the Context7 MCP server?
No. You keep running the same server, unchanged. Prismor aggregates it behind a single connector so your agent sees the same tools, namespaced as mcp__<server>__<tool>, with every call and every result passing through policy first.
Will this block work my team actually needs to do?
Not if you start in observe mode. Every call is recorded with the decision that would have applied, and nothing is blocked. You promote rules to enforce once the log shows the policy matches how your agents really work.
What about tool results, not just tool calls?
Results are scanned as untrusted content before the model sees them. A response carrying injected instructions or poisoned output is withheld and replaced with the reason, which matters most for servers that return text other people wrote.
One gateway for every MCP server
Context7 is one connector. The same policy covers the rest of them, plus the shell commands and file access your agents already have.
Other knowledge servers
Notion
Obsidian
Google DriveContext7 is a trademark of its respective owner. Prismor is not affiliated with or endorsed by it. The Context7 MCP server is third-party software; Prismor governs it the same way it governs any MCP server, without modifying it.