Context Firewall MCP server
io.github.Alepha188838884/context-firewall·v0.1.1·2 starsLocal MCP proxy: collapses N servers' tools into 4 meta-tools and compresses large tool outputs.
2 stars38 downloads/wk
Reviews
Write oneNobody has reviewed Context Firewall yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Context Firewall tools (4)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
invoke_toolInvoke a downstream tool. Large outputs are compressed; full output retrievable via read_more with the returned handle.
list_tool_categoriesList all downstream MCP servers with status, tool counts, and capability categories. Call this first to discover what is available.
read_moreRetrieve a slice of a stored full output by handle (character offsets).
search_toolsSearch downstream tools by keyword; returns full input schemas for matches. Use before invoke_tool.
Public scan report
scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it
- Code scan21 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 22 days ago15/15
- Maintainer identityregistry namespace matches repository owner6/10
How Context Firewall compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 89/100
- higher than 80% of 48,255 servers
- Tools
- 4
- the typical server has 7
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 2
- more than 75% of 28,688 servers
- Downloads a week
- 38
- more than 29% of 12,191 servers with a package
What its tools let an agent do: 3 read · 1 run or deploy
Install Context Firewall in Claude Code, Cursor or VS Code
Runs npx -y context-firewall on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add context-firewall -- npx -y context-firewall
What the publisher says
From the Context Firewall repository's README, as published. We do not edit it. Read it on GitHub
Context Firewall
中文文档
Shrink large MCP tool outputs by 60–95% before they reach your model's context window — and collapse 50+ tool definitions into 4. Real HTML/JSON, measured — see benchmarks. Works with any MCP client, any model. Anything still over your configured token budget after compression is hard-truncated to that budget, with the full original always retrievable via read_more.
The session report printed on shutdown — this one from a real 3-call session (two large file reads, one echo). Every number measured, none simulated.
Context Firewall is a local MCP proxy that sits between your AI agent (Claude Code, Claude Desktop, Cursor, Cline, ...) and every downstream MCP server you've configured. Large tool outputs (raw HTML, base64 blobs, giant JSON) are compressed before they ever reach the model's context window, and the client sees exactly 4 tools no matter how many the downstream servers actually have.
Measured results
All figures measured against real downstream MCP servers, not synthetic data — full methodology and tables in docs/BENCHMARKS.md.
What it does
- Progressive tool disclosure — instead of loading every downstream tool's full schema at startup, the client sees 4 meta-tools (listtoolcategories, searchtools, invoketool, read_more) and only pays the token cost of a tool's full schema when it actually searches for it.
- Output compression pipeline — large tool results are run through base64 stripping, main-content extraction + HTML→Markdown conversion (page chrome — nav, site headers/footers — is stripped when the page has a recognizable content region, so your token budget goes to actual content instead of navigation links), JSON structure-aware summarization, and finally character-budget truncation, in that order, before being returned.
- Full output retrievable via readmore — nothing is silently thrown away. Every compressed output is stored in full (in memory, opaque handle) and can be paged back with readmore(handle, offset, length).
- Session savings report — on shutdown, prints a shareable terminal card (and optional Markdown file) showing tool-definition and output-token savings for the session, plus a breakdown of which tools saved the most.
Quickstart
npx context-firewall --config context-firewall.jsonShortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Context Firewall: common questions
- Is Context Firewall MCP server safe?
- Yes, by our scan: it is graded A (89/100). Read the Context Firewall safety report
- How do I install Context Firewall?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Context Firewall need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Context Firewall maintained?
- The last commit was 62 days ago (2026-09-03). The latest release is v0.1.1.
- How does Context Firewall compare with other MCP servers?
- safety score 89/100 (higher than 80% of 48,255 servers); tools 4 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.