Enables read-only AWS FinOps scans for hidden costs such as NAT Gateway endpoint traffic, infinite log retention, gp2/orphaned EBS volumes, idle Elastic IPs, and stale snapshots, with USD/month estimates and Terraform or CloudFormation remediation patch generation.
Read-only attack-path tools for cloud and Kubernetes: list the reachable routes from internet exposure to sensitive assets, explain each hop and the evidence behind it, and simulate a fix before recommending it. Connects to a running PerspectiveGraph engine.
Anchor AI FinOps to real, live cloud pricing. AWS, GCP & Azure — public list prices and enterprise negotiated rates. No credentials needed for AWS and Azure public pricing.
I gave Claude a mass grave of 200 markdown files and now it remembers my entire project between sessions. No cloud, no API keys, one 10mb Go binary, and private. Stateless Agent Memory Engine is your synapse to the CLI.
MCP server built into the Nhost CLI. Lets AI coding assistants read your GraphQL schema, run the queries and mutations you allow, manage permissions and migrations locally, update Nhost Cloud project config, and search the Nhost docs.
Enables AI assistants to manage and query Tiger Cloud database services, including service lifecycle operations, database connections, and SQL execution.
A Model Context Protocol server for Massdriver that enables AI assistants to manage infrastructure platform resources like projects, environments, deployments, policies, and more. It provides 106 tools and supports stdio or HTTP transports.
Open source SQL-native query and provisioning engine for cloud and SaaS infrastructure. Ships as a single signed binary with MCP tools for provider discovery, schema exploration, queries, and lifecycle operations.
Lets AI assistants read Costfluent cloud cost data — costs over time, saved cost reports, budgets, anomalies, the savings queue, commitments and coverage, and Kubernetes efficiency — and, where an Owner allows it, create and change annotations, cost reports, budgets, cost alerts and dashboards. It runs locally over stdio on the API token you supply, offering only the tools the token's capabilities and the organization setting permit, and never deletes anything.
Enables MCP clients to scaffold trading strategies, run backtests locally or in cloud workspaces, fetch session analytics, and manage research labs against an algorithmic trading platform backend.
Enables AI assistants to automatically call Carbonstop Cloud API for carbon footprint modeling, product query, and emission analysis through natural language.
Enables AI assistants to inspect PRRO.cloud cash registers, shifts, fiscal tasks, billing, and webhook deliveries through a read-only API, helping developers build and debug PRRO integrations.
Enables AI agents to explore and, when writes are enabled, modify a Langfuse deployment — traces, observations, sessions, prompts, datasets, scores, metrics and more — through the full Langfuse public API. Supports Langfuse Cloud in any region and self-hosted instances, including corporate networks that re-sign TLS traffic with their own certificate authority.
A native, local-first, multilingual memory server for Codex, Claude Code, and any MCP client, providing hybrid semantic and exact memory recall using Go, Qdrant, and bge-m3. It enables stable, concurrent memory storage and retrieval without Docker or cloud dependencies.
Enables assistants to read account data (tunnels, usage, metrics, tokens, invoices, domains, notifications, cloud apps) and start/stop tunnels via the tunnels.io API and CLI.
Enables local, read-only analysis of Codex and Claude Code conversations through ten MCP tools for browsing sessions, inspecting tokens and tools, and comparing sessions without accounts or cloud services.
Keeps Jira Cloud, Jira Server, Linear or its own built-in tracker (plus Confluence pages) in one local SQLite file. Its MCP tools answer from that file: read-only SQL, full-text search across issues, comments and wiki pages, issue detail, sprint and retro reads.
Enables AI agents to edit video locally through FFmpeg: probing media, validating and previewing JSON edit projects, rendering short-form clips with captions, reframing, transitions and ducked music. Also analyses existing videos and applies or saves reusable format templates, without cloud services or API keys.
Local-first, file-based memory layer for AI agents — one shared Markdown vault across Claude, Codex, Gemini, Cursor and any MCP client. Provides read/write memory tools with an audit trail, per-agent trust levels, and Git sync; no cloud and no lock-in.
Enables AI assistants to contribute to Google Cloud Platform's k8s-config-connector by adding fields to resources, migrating from Terraform to direct controller architecture, and creating properly attributed commits.
Provides persistent memory for AI tools by building a local knowledge graph from conversations, enabling cross-session recall and context awareness without cloud dependencies.