# Silmaril

**Canonical:** https://apis.io/providers/silmaril/  
**Website:** https://silmaril.dev/docs  
**APIs profiled:** 1

Silmaril is a Y Combinator-backed runtime security company that builds an AI application firewall for agentic systems. The Silmaril Firewall classifies prompts, retrieved context, tool calls, tool responses, model output, and accumulated execution state before harmful outcomes materialize, returning a benign/malicious prediction plus a primary-outcome classification across secret exposure, information disclosure, control abuse, system compromise, and service disruption. It ships first-party TypeScript, Python, Go, and Java SDKs, LiteLLM and Vercel AI gateway guardrails, LangChain/LangGraph handlers, and agent plugins for Codex, Claude Code, OpenClaw, and Hermes, plus a hosted read-only MCP evidence server. Offered as managed and customer-controlled self-hosted container deployments.

## Kin Score — 32.2 / 100 (thin)

Scored 2026-08-20 under rubric 0.12.0. Trend: flat (+0.0 from 32.2).

| Facet | Score |
|---|---|
| Discoverability | 75.9 |
| Contract Quality | 0.0 |
| Governance | 18.2 |
| Contract Governance | 18.2 |
| Operational Transparency | 44.7 |
| Developer Ergonomics | 61.9 |
| Commercial Clarity | 21.1 |
| Access Clarity | 21.1 |

## Agent readiness — 22.2 (agent-aware)

| Dimension | Value |
|---|---|
| Spec Presence | no |
| Agentic Access | no |
| Reversibility Documented | no |
| MCP Server | verified |
| Auth Clarity | yes |
| Idempotency | no |
| Error Semantics | documented |
| OpenAPI Examples | no |
| Rate Limit Signal | no |
| Event Surface Described | no |
| Agent Skills | no |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |

## Access

Self-serve signup — onboarding: self-serve, pricing: unknown, trial: no (confidence: medium).

## APIs (1)

- **Silmaril Firewall API** — AI application firewall classify API. A Firewall client sends each sanitized classification input (user input, tool response, model output, or system prompt) with a hook label a...

## MCP servers (1)

- **Silmaril MCP Server** — Hosted, read-only, tenant-scoped MCP server that lets an agent read Silmaril Firewall security evidence (findings, metrics, suspicious users, investigation packets, traces) from...

## Security (3)

- **Silmaril Authentication** — apiKey/oauth2 · 2 schemes
- **Silmaril Domain Security** — TLSv1.3 · HSTS
- **Silmaril Vulnerability Disclosure** — contact published

## Tags

Company, AI Security, AI Firewall, Prompt Injection, Agent Security, Runtime Security, Guardrails, MCP, LLM Security, Developer Tools

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/silmaril/). Scores are computed from the provider's own public artifacts under a published rubric.