BLA
BLA (Blind LLM Agents) is the open-source Blue Defense MCP and CLI built to protect software artifacts against automated AI reverse-engineering workflows.
翻譯準備中
MCP gateway between AI agents and their tools, the web and Matrix: three-layer prompt-injection defense, smaller tool lists and responses, gateway-enforced parameter and response guards, OAuth/DCR, an
翻譯準備中
安全Python · JavaScriptGitHub @crunchtools自行安裝營運者未確認
試用過了嗎? 點一下就好,不需要登入。
MCP gateway between AI agents and their tools, the web and Matrix: three-layer prompt-injection defense, smaller tool lists and responses, gateway-enforced parameter and response guards, OAuth/DCR, and per-agent profiles
翻譯準備中
取自儲存庫 README
正在載入完整 README。 以下為已儲存的摘錄。
Trentina is an MCP gateway that sits between your AI agents and everything they
touch: MCP servers, the web, Matrix, LLM providers and monitoring alerts. Every
agent gets one endpoint and its own profile. Behind that endpoint Trentina
stops prompt injection at every ingress and shrinks what reaches the context
window. It also enforces policy the agent cannot talk its way past and handles
OAuth for web clients like claude.ai and gemini.google.com. The same gateway
can serve a personal assistant, a coding agent and a swarm, wired however you
like.檢視完整 README ↗Trentina sits between your AI agents and everything they touch: MCP servers, the web, Matrix, LLM providers and alerts. It stops prompt injection at every ingress — or at a trusted boundary you declare — shrinks what reaches the context window, and enforces a policy the agent cannot talk its way past. It is named after the 1377 trentino of Ragusa, where ships anchored offshore for thirty days before anyone came ashore: commerce keeps flowing, and nothing dangerous gets in.
Security. Untrusted content crosses three independent layers at every ingress to the trust boundary, which can be federated with other instances: L1 deterministic checks, L2 a local classifier, L3 a quarantined LLM with no tools. Semantic request guards judge what goes out against a rule you write in English. What is and is not defended is in Coverage. Defense Pipeline · Benchmark · OWASP mapping
Token savings. Hidden tools, short names, compacted schemas, compressed descriptions and minified responses: on production traffic. ·
Determinism. Literal request guards, literal response guards and allowlists are evaluated by the gateway, so an agent that ignores its instructions is stopped before the backend sees the call. Literal Request Guards · Literal Response Guards
Authentication. Trentina is the OAuth authorization server for web clients such as claude.ai: dynamic client registration, a provisioned client, external issuers or a static bearer, chosen per profile. Authentication
Architectural flexibility. A personal assistant, a coding agent and a swarm each get their own profile, with their own backends, defense mode and credentials — and an operator agent configures all of it through tools, with no shell. Profiles · Operator
# The container image is the distribution: the L2 model, the parsers and
# their process isolation ship in it. There is no PyPI package.
podman run -d -p 127.0.0.1:8019:8019 \
-v ./profiles.yaml:/config/profiles.yaml:ro,Z \
-e TRENTINA_GATEWAY_ENABLED=true \
-e TRENTINA_PROFILES_PATH=/config/profiles.yaml \
-e TRENTINA_PROFILE_MYAGENT_TOKEN=your-token \
-e OPENROUTER_API_KEY=your-key -e TRENTINA_MODEL_PROVIDER=openrouter \
quay.io/crunchtools/trentina \
--transport streamable-http --host 0.0.0.0 --port 8019
L3 needs a key for one LLM provider. Any of Gemini, OpenRouter, OpenAI,
Anthropic or Ollama works. A minimal profiles.yaml:
profiles:
myagent:
auth:
bearer_token_env: TRENTINA_PROFILE_MYAGENT_TOKEN
backends:
web:
url: "internal://web" # Trentina's own content tools
tools_allow: ["*"]
gmail:
url: "http://gws-personal:8000/mcp"
tools_allow: # it may read and draft; you send
- search_gmail_messages
- get_gmail_message_content
- draft_gmail_message
defense:
enforcement: block
Then point Claude Code at it:
{
"mcpServers": {
"trentina": {
"type": "streamable-http",
"url": "http://localhost:8019/gateway/myagent/mcp",
"headers": { "Authorization": "Bearer your-token" }
}
}
}
| Document | Description |
|---|---|
| MCP Gateway | One endpoint per profile: routing, tool names, circuit breakers |
| Per-Agent Profiles | Profile schema, modes, minifying, roles, multi-agent setup |
| Operator Profile | The agent that installs and runs the gateway |
| Configuration | Every environment variable |
| Authentication | Static bearer, OAuth proxy with DCR or a provisioned client, delegated issuers |
| Backend OAuth | Each profile signs in to OAuth-only backends with its own grant |
| Defense Pipeline | L1/L2/L3, modes, coverage and known gaps |
| Benchmark | Detection rates per layer and per L3 provider |
| Corpora | Every attack and benign set the defense is measured on |
| Prompt Packs | The judge's prompts tuned per model |
| Content Tools | fetch, read, dir, content, search, with an egress guard and file confinement |
| Blocklist | A refused source stays refused |
| Tool Filtering | Allowlists, denylists, glob patterns |
| Tool Pinning | A new or changed tool is held until approved |
| Tool Discovery | Find/call or per-session loading for clients without tool search |
| Description Compression | Description compression and schema compaction |
| Token Routing | Response minifying (implemented); delegation (proposed) |
| Semantic Request Guards | A judge reads calls to listed tools against a policy in plain English |
| Semantic Response Guards | A judge reads listed tools' responses against a policy before delivery |
| Literal Request Guards | Per-tool argument validation |
| Literal Response Guards | Per-tool result validation |
| Audit Log | Call recording, stats, monitoring |
| LLM Key Proxying | Provider keys kept inside the gateway |
| Matrix Bridge | E2EE termination and two-way judging |
| Channel Bridges | More than one upstream per agent (RCS, ...) and the bridge wire contract |
| Matrix Reverse Proxy | Matrix for agents on an isolated network |
| Client Egress | A CONNECT tunnel to listed hosts for the agent's own client |
| Git Transport | Clone, fetch and push to listed repositories and branches |
| Federation | A second gateway's tools mounted over a trusted edge, scanned once |
| HTTP(S) Egress | An agent's outbound request judged and re-originated to a named destination |
| Deployment Hardening | Container flags, secrets, egress, the startup check |
| Plugins | Write, test, install and name your own transform plugins |
| Cockpit Plugin | Live defense pipeline dashboard |
| Internal: Gateway Design | Original design document, for contributors |
uv sync --all-extras
uv run ruff check src tests
uv run mypy src
uv run pytest -v
The container image is built by CI, never locally; see CLAUDE.md. The demo
is recorded by demo.yml; its fixtures are in
docs/demo/.
AGPL-3.0-or-later