SkillAgentSearch skills...

systemprompt-core

AI governance infrastructure for agentic systems. Rust library behind systemprompt.io — MCP, A2A, OAuth2, audit trails, compile-time extensions. Evaluate with systemprompt-template.

Install / Use

claude mcp add systempromptio -- npx -y github:systempromptio/systemprompt-core

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

79/100

Supported Platforms

Claude Code
Claude Desktop

Our assessment of systemprompt-core

systemprompt-core scores 79/100 on our quality scale, 766th of 950 AI & Machine Learning skills we index.

Its MCP Server is 6.3 KB long, split into 7 sections with 3 code examples: a thorough specification that gives an agent plenty to work with.

It has 10 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
29/30
Structure
16/20
Description
15/15
Adoption
4/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated today, so systemprompt-core is actively maintained.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 85/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-11-17. Automated pattern scan on 2026-11-17. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

systemprompt-core compared with similar skills

All 4 of these similar skills score higher than systemprompt-core; compare them before choosing.

SkillScoreStarsUpdatedFormat
systemprompt-core (this skill)by systempromptio7910todayMCP Server
claude-memby thedotmack100117.9ktodayCLAUDE.md
Agent-Reachby Panniantong100112.7k9d agoCLAUDE.md
Understand-Anythingby Egonex-AI10093.0k2d agoCLAUDE.md
rufloby ruvnet10082.0ktodayCLAUDE.md

Frequently asked questions

How do I install systemprompt-core?
Run claude mcp add systempromptio -- npx -y github:systempromptio/systemprompt-core. The install tabs above show the steps for each supported agent.
Which AI agents does systemprompt-core work with?
It is written for Claude Code and Claude Desktop, as a MCP Server file. Other agents that read the same format can often use it too.
Is systemprompt-core safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 85/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is systemprompt-core still maintained?
The repository was last updated today, so systemprompt-core is actively maintained.
<div align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://systemprompt.io/files/images/logo.svg"> <source media="(prefers-color-scheme: light)" srcset="https://systemprompt.io/files/images/logo-dark.svg"> <img src="https://systemprompt.io/files/images/logo-dark.svg" alt="systemprompt.io" width="400"> </picture>

SystemPrompt Core

SystemPrompt Core is the Rust library for a control plane you operate: identity, model access, MCP tool execution, policy and audit, with your domain capabilities compiled alongside them.

Crates.io Docs.rs License: BSL-1.1

Evaluate · API docs · Architecture · Security

</div>

Capabilities

Connect supported AI clients to your gateway and expose governed MCP tools. Core binds requests to identity, evaluates access and records decisions and usage in PostgreSQL. You operate the runtime, choose the upstream providers and retain the audit data.

| Capability | Interface | |---|---| | Identity | OAuth2/OIDC, authenticated sessions and access rules for users and resources. | | Model gateway | Anthropic-compatible /v1/messages, model discovery and configurable upstream routing. | | MCP and agents | Governed tool access and hosted agents with A2A transport. | | Enforcement | Scope checks, credential-pattern detection, blocklists and rate limits on governed tool calls. | | Audit | Correlated request and tool records linking identity, decisions, results and inference usage. | | Composition | Your routes, providers, tools, jobs and persistence registered through extension contracts. |

Governance applies to traffic routed through these surfaces. Client-side tool execution needs the corresponding integration; a model gateway alone cannot govern every action on a laptop.

Extension model

SystemPrompt Core + your extensions + your configuration
                           ↓
                 Your compiled runtime
                           ↓
                      PostgreSQL

Build company-specific behavior on the same extension contract used by Core's own domains. The AI domain, for example, registers its schemas, migrations and dependencies through Extension.

An extension can contribute API routes, model and tool providers, scheduled jobs, configuration validation, schemas, migrations and roles. Gateway request guards let you add application-specific decisions before inference dispatch. The demo's credit extension shows that hook in use.

Registration happens at compile/link time through inventory. At startup, the runtime discovers registrations and validates their dependency graph. See the extension API source for the contract and registration flow.

Compiled extensions are trusted Rust code sharing your process. External MCP servers can run separately. This gives you a compact deployment while keeping process isolation available where the integration needs it.

Use as a library

The workspace publishes a systemprompt facade with feature-gated systemprompt-* crates:

[dependencies]
systemprompt = { version = "0.83", features = ["full"] }

| Feature | Includes | |---|---| | core (default) | Shared traits, models, wire codecs, services manifest, identifiers and extension contracts. | | database | PostgreSQL integration. | | api | HTTP server and application context. | | cli | Command-line entry point. | | files-office | Word, Excel, PowerPoint and OpenDocument codecs for the shared document store; included in full. | | full | Bundled runtime, domain modules and CLI, including the shared document store; the Slack and Teams modules remain opt-in. |

Use YAML to configure a deployment and Rust extensions to add behavior. Your host links those extensions and delegates startup to Core; the template entry point is a working example.

Evaluate and build

For a running system with configuration, admin UI and scripted enforcement demos, start with the MIT-licensed evaluation template.

To compile this workspace:

git clone https://github.com/systempromptio/systemprompt-core
cd systemprompt-core
just build-offline

Install Rust through rustup and just. The repository pins its toolchain in rust-toolchain.toml and declares Rust 1.96+ with edition 2024. build-offline uses the committed SQLx query cache without a running database; dependency downloads may still require network access. Runtime deployments require PostgreSQL 18+.

The runtime can operate inside a private network or air gap when models, tools and dependencies are available there. Requests routed to cloud providers leave that perimeter. Tool servers may introduce their own runtime dependencies.

Evaluate the boundary

Tool credentials can be supplied to child-process environments without placing them in model context. Credential-pattern scanning provides an additional check on governed arguments; the tool process and its outputs remain trusted parts of the deployment.

Review the evaluation documentation, production deployment guide and template benchmarks against your own requirements. Report vulnerabilities through SECURITY.md.

License

Core is BSL-1.1 source-available, available for evaluation, testing and non-production use under its license terms. Production use requires a commercial license. Each version converts to Apache-2.0 four years after publication.

You control your deployment and extensions; Core's license governs use of the underlying library. Discuss production licensing.

Related Skills

View on GitHub
GitHub Stars10
CategoryAI
Updated9h ago
Forks2

Languages

Rust

Trust signals

85/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 medium1 info