CCM
/MCP
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Claude Code Marketplaces

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Skill index
  • MCP index
  • Marketplace index
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by mertbuilds.com

Independent project, not affiliated with Anthropic
ariffazil avatar

Aaa Mcp

ariffazil/arifos
454 toolsSTDIO, SSEregistry active
Summary

A constitutional AI framework that enforces 13 governance floors (F1-F13) across LLM operations through a tri-witness consensus model weighing human, AI, and environmental factors. Exposes 13 MCP tools spanning session init, reasoning, evidence fetching, routing, memory recall, ethical critique, and a 888_JUDGE gate that issues SEAL/HOLD/VOID verdicts on proposed actions. Tier 3 operations requiring irreversible execution hit the judge first, get a verdict hash, then route through arif_forge_execute with explicit human acknowledgment. The VAULT999 ledger anchors decisions immutably. Reach for this when you need auditability, forced uncertainty quantification, or hard constraints on what an agent can do without human override. Runs on port 8088, supports stdio and SSE transports.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →

Tools

Public tool metadata for what this MCP can expose to an agent.

4 tools
add-templateAdd a new template with sections to an existing tenant via the seed-template endpoint6 params

Add a new template with sections to an existing tenant via the seed-template endpoint

Parameters* required
accessTokenstring
JWT access token from admin user
sectionsJsonstring
JSON array describing sections and items. Example: [{"name":"Section","items":[{"label":"Doc","isRequired":true}]}]
serviceTypeDescriptionstring
Service type description
serviceTypeNamestring
Service type name
templateNamestring
Template name
tenantIdstring
Tenant identifier (UUID)
auth-loginAuthenticate user via the login endpoint and get JWT access token2 params

Authenticate user via the login endpoint and get JWT access token

Parameters* required
emailstring
User's email
passwordstring
User's password
create-tenantCreate a new tenant via the bootstrap endpoint with tenant, service type, admin user, and document sections14 params

Create a new tenant via the bootstrap endpoint with tenant, service type, admin user, and document sections

Parameters* required
accessTokenstring
JWT access token from login
adminAddressstring
Address (default: 123 Main St)
adminEmailstring
Admin user email
adminFirstNamestring
Admin first name
adminLastNamestring
Admin last name
adminPasswordstring
Admin user password
adminPhonestring
Phone number (default: +1-555-0100)
sectionsJsonstring
JSON array describing sections and items. Example: [{"name":"Section","items":[{"label":"Doc","isRequired":true}]}]
serviceTypeDescriptionstring
Service type description
serviceTypeNamestring
Service type name (e.g., 'Tax Advisor')
templateNamestring
Template name (e.g., '2024 Onboarding Checklist')
tenantLogoUrlstring
Logo URL (default: https://platform.clara.care/logo.svg)
tenantNamestring
Tenant name
tenantUrlstring
Tenant URL or slug
http-requestMake HTTP requests to external APIs4 params

Make HTTP requests to external APIs

Parameters* required
bodystring
Request body as JSON string
headersobject
HTTP headers
methodstring
HTTP methodone of GET · POST · PUT · DELETE
urlstring
The URL to make the request to

arifOS — Law

Judge before acting. Never act.

The constitutional kernel of the arifOS Federation.

arifOS is law, not an agent. It judges. It seals. It never executes.

DITEMPA BUKAN DIBERI — Forged, Not Given.


Every action, three questions

Every consequential action must answer:

  1. Who performs it?
  2. Who approved it?
  3. Who witnessed it?

arifOS answers the second — and only the second.

Execution belongs to A-FORGE. Routing belongs to AAA. Authority belongs to the sovereign.

The agent that acts is not allowed to certify its own action.

Verdicts

Four. No fifth.

  • SEAL — authorized under stated conditions
  • HOLD — insufficient evidence, or human approval required
  • SABAR — proceed cautiously, partial authorization
  • VOID — blocked by a constitutional floor

Verbs (MCP)

Eight canonical verbs, live-witnessed 2026-08-25 via :8088/health:

arif_init · arif_observe · arif_think · arif_route · arif_memory · arif_judge · arif_forge · arif_seal

Door: /mcp. Public console is not exposed — the kernel serves /webmcp on :8088 locally only.

30-second proof

Request: "delete production database"
  No session ACT, no evidence chain → HOLD
  Evidence + floors pass → SEAL with conditions
    → execution by A-FORGE → receipt → VAULT999

VAULT999 (live 2026-08-25): healthy, append-only, outcomes.jsonl 67K+ records, 0 broken lines.

Architecture in one sentence

The judge never executes; the executor never certifies.

flowchart LR
    Intent[Intent] --> Judge[arifOS]
    Judge -->|SEAL| Forge[A-FORGE]
    Forge --> Receipt[Receipt]
    Receipt --> Vault[VAULT999]
    Judge -->|HOLD| Human[Human Review]

Federation card

ARIF = Sovereign · arifOS = Law · AAA = Institution · A-FORGE = Hands

ARIF vetoes. arifOS judges. AAA routes. A-FORGE executes.

Full card: docs/FEDERATION_CARD.md · Full reference README: docs/README-FULL.md · Constitution: GENESIS/000_KERNEL_CANON.md · ZEN doctrine: docs/ZEN.md

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
Registryactive
Packagearifos
TransportSTDIO, SSE
UpdatedFeb 10, 2026
View on GitHub

More from ariffazil

  • arifOS — Constitutional AI Governance