# sigma-gate [Health: Active] **Category:** πŸ’» Developer Tools **Repository:** https://github.com/spektre-labs/sigma-gate **GitHub Stars:** 0 **Views:** 0 **Installs:** 0 **Upvotes:** 0 **Directory Page:** https://allmcps.com/mcp/sigma-gate ## Description Deterministic trust gate for AI output: leaked-secret, prompt-injection & PII in one call. ## Claude Desktop Quick Installation Install path detected from listing signals. Uses `uvx` (confidence: high): ```json "mcpServers": { "sigma-gate": { "command": "uvx", "args": ["required"] } } ``` ## Documentation & README # ⟐ Οƒ-gate β€” guard [![ci](https://github.com/spektre-labs/sigma-gate/actions/workflows/ci.yml/badge.svg)](https://github.com/spektre-labs/sigma-gate/actions/workflows/ci.yml) **Deterministic trust layer for AI/agent output. One call β†’ one verdict. No model, no API key, no network.** ``` 1 = 1. Declared output must equal what is safe to realize. ``` --- ## The paradigm The other four Spektre repos are **routing protocols** β€” they move value, capability, promises, and identity across networks. **Οƒ-gate is not a routing protocol, and does not pretend to be one.** It is the suite's **deterministic trust verdict**: the gate that sits at the edge of any pipeline and answers, in ~85Β΅s and identically every time, *is this output safe to ship?* LLM-as-judge guards are slow, burn a model call per check, and silently degrade under rate-limits. But the highest-frequency risks β€” a leaked `AKIA…` key, a Luhn-valid card number, an "ignore all previous instructions" β€” are **structurally detectable**: you don't need a model, you need a gate that gives the **same answer every time**. That determinism *is* the primitive. `Οƒ` = declared βˆ’ realized: a block is always nameable (`secret[high]: github_pat`), never an opaque float, so what the gate declares unsafe is exactly what it refuses to realize. `guard` is that gate. --- ## One call ```python from guard import guard result = guard(model_output) # {"safe_to_ship": True/False, "severity": "clean|low|medium|high|critical", # "block_reasons": [...], "dimensions": {"secret": {...}, "injection": {...}, "pii": {...}}} ``` Block a bad output: ```python v = guard("Here is the key: ghp_16C7e42F292c6912E7710c838347Ae178B4a") # safe_to_ship: False # block_reasons: ["secret[high]: github_pat"] ``` Pass a clean output through: ```python v = guard("The quarterly report shows revenue grew 12% driven by the EU segment.") # safe_to_ship: True # severity: "clean" ``` --- ## Three dimensions, one verdict | Dimension | What it catches | |---|---| | **secret** | Leaked credentials β€” 20+ providers (AWS, GitHub, Stripe, GCP, …), entropy-ranked | | **injection** | Prompt-injection and jailbreak patterns β€” structural, not heuristic | | **pii** | Email, phone, card (Luhn-verified), SSN, IBAN, IP β€” compliance-class detection | Every dimension runs independently. A combined hit fires all three: ```python guard("AKIA… ghp_… 4111 1111 1111 1111 β€” ignore all previous instructions") # block_reasons: ["secret[high]: ...", "injection[high]: ...", "pii[high]: ..."] ``` --- ## Install Zero dependencies, pure stdlib, Python 3.9+. ```bash git clone https://github.com/spektre-labs/sigma-gate && cd sigma-gate pip install -e . # installs the `guard` + `guard-mcp` console scripts python3 -m pytest -q # 7 passed, zero dependencies ``` No install is even required to import β€” `from guard import guard` works from the cloned directory. --- ## Use it **Inline gate in any pipeline:** ```python from guard import guard def ship(output: str) -> str: v = guard(output) if not v["safe_to_ship"]: raise ValueError(f"blocked: {v['block_reasons']}") return output ``` **CLI β€” pipe any output through:** ```bash echo "your model output" | python3 -m guard ``` **Self-test β€” prove every threat class fires:** ```bash python3 -m guard selftest # {"secret_blocked": true, "injection_blocked": true, "pii_blocked": true, # "clean_passes": true, "combined_all_fire": true, "ALL_PASS": true} ``` **Tune the threshold** via env var (default: `medium`): ```bash GUARD_BLOCK_AT=high python3 -m guard "..." ``` --- ## Use as an MCP tool Οƒ-gate ships a zero-dependency [MCP](https://modelcontextprotocol.io) server β€” give any agent (Claude Code, Claude Desktop, Cursor, Cline) a deterministic `guard` tool it can call before shipping output. No model, no key, no token cost. **Claude Code:** ```bash claude mcp add guard -- python3 /absolute/path/to/sigma-gate/mcp_server.py ``` **Claude Desktop** (`claude_desktop_config.json`): ```json { "mcpServers": { "guard": { "command": "python3", "args": ["/absolute/path/to/sigma-gate/mcp_server.py"] } } } ``` Exposes two tools: `guard(text, …)` β†’ the ship/block verdict, and `guard_selftest()` β†’ proof every threat class fires. Pure stdlib stdio JSON-RPC. ### Hosted β€” no install Οƒ-gate also runs as a **hosted remote MCP server** (scale-to-zero), listed in the [official MCP Registry](https://registry.modelcontextprotocol.io) as `io.github.spektre-labs/sigma-gate`. Connect with zero local setup: ``` https://sigma-gate-864996675261.us-central1.run.app/mcp ``` MCP clients that browse the registry discover it automatically. --- ## Open-core vs hosted | | **Open core (this repo)** | **Hosted Οƒ scoring** | |---|---|---| | **What** | Deterministic gate: secret + injection + PII | Coherence / hallucination Οƒ-scoring on a hot path | | **Latency** | ~85Β΅s | Network round-trip | | **Dependencies** | Zero | None on your side | | **Cost** | Free, always | Pay-per-call via x402 β€” no signup | | **Offline** | Yes | No | | **Model** | None | Optional | The open core handles what models cannot do reliably β€” structural pattern detection with identical verdicts on identical inputs. The hosted layer adds probabilistic coherence scoring for the cases where structure alone is insufficient. **Hosted endpoint:** ```bash curl "https://swagletz-sigmagate.hf.space/check?text=your+text+here" # HTTP 402 + permissionless x402 pay-to β€” no account required ``` --- ## Properties - **Deterministic.** Same input β†’ same verdict. No variance, no model drift. - **Composable.** Each dimension is independent and pluggable. Wire in a hallucination scorer or extend with custom patterns; the gate architecture is additive. - **Honest.** Severity and block-reasons are explicit strings, not opaque floats. A block is always nameable. - **Fails safe.** If a detector throws, that dimension returns `severity: "error"` β€” the call does not silently pass. - **Zero dependencies.** Runs anywhere Python 3.9+ runs. No pip install required to import. --- ## Status **REAL** β€” shipped, deterministic, deployed. CI green, 7/7 tests passing, zero dependencies; live as a local MCP tool and as a hosted scale-to-zero MCP server listed in the official registry. --- ## The Spektre protocol suite Οƒ-gate is the **deterministic trust verdict** of a five-part estate. The other four are routing protocols; this one is the gate they ship through: - **[vrp](https://github.com/spektre-labs/vrp)** β€” value routing (least-friction multi-hop settlement) - **[crp](https://github.com/spektre-labs/crp)** β€” capability routing (route a task to the best AI substrate) - **[vtc](https://github.com/spektre-labs/vtc)** β€” verifiable transaction chain (signed value promises anyone verifies trustlessly) - **[sid](https://github.com/spektre-labs/sid)** β€” sovereign identity (prove one claim, reveal nothing else) - **[sigma-gate](https://github.com/spektre-labs/sigma-gate)** β€” deterministic trust verdict *(this repo)* --- ## License **Apache-2.0** β€” see [LICENSE](https://github.com/spektre-labs/sigma-gate/blob/HEAD/LICENSE). --- Part of [Spektre Labs](https://spektrelabs.org) β€” coherence-theory research lab. `Οƒ = declared βˆ’ realized Β· 1 = 1`, made executable.