Search the registry

Context7

1.0.0

Upstash

MCP

Pulls current, version-pinned library docs at query time so the agent stops hallucinating package APIs.

Dune

1.0.0

Dune

MCP

Run and read Dune Analytics queries from the agent. API credits are metered — a chatty agent burns a free tier fast.

Gmail

1.0.0

GongRzhe

MCP

Read and send mail from Gmail (OAuth on first call). Community-maintained — never let an agent send mail unsupervised.

Mistral AI

1.0.0

Swih

MCP

Full Mistral AI surface — chat, embeddings, vision, OCR, Voxtral audio (transcribe/speak), Codestral FIM, agents, moderation, files, and batch. 22 tools. Listed on the Official MCP Registry. Free Experiment tier: 1B tokens/month.

Neon

1.0.0

Neon

MCP

Serverless Postgres with branch-based migrations — the agent tests migrations on an instant copy-on-write branch before applying.

PayPal

1.0.0

PayPal

MCP

Invoices, transactions, and payouts via PayPal's official MCP / agent toolkit. Moves real money — confirm every write.

Sentry

1.0.0

Sentry

MCP

Pipe issues, stack traces, and event detail into the agent — read a prod error and propose the fix. Pairs well with GitHub.

Solana Agent Kit

1.0.0

SendAI

MCP

Onchain actions on Solana — transfers, swaps, token ops. Irreversible chain; prefer setups that sign in a separate wallet and never put a funded key in config.

Use when working with Chainlink oracle networks, CCIP cross-chain messaging, or smart contract data feeds. Official Chainlink agent skills on the agentskills.io spec.

Delegate coding to Claude Code CLI (features, PRs).

Delegate coding to OpenAI Codex CLI (features, PRs).

Debug Hermes TUI slash commands: Python, gateway, Ink UI.

DSPy: declarative LM programs, auto-optimize prompts, RAG.

Generate and prioritize US equity long-side edge research tickets from EOD observations, then export pipeline-ready candidate specs for trade-strategy-pipeline Phase I. Use when users ask to turn hypotheses/anomalies into reproducible research tickets, convert validated ideas into `strategy.yaml` + `metadata.json`, or preflight-check interface compatibility (`edge-finder-candidate/v1`) before running pipeline backtests.

Aggregate and rank signals from multiple edge-finding skills (edge-candidate-agent, theme-detector, sector-analyst, institutional-flow-tracker) into a prioritized conviction dashboard with weighted scoring, deduplication, and contradiction detection.

Convert abstract edge concepts into strategy draft variants and optional exportable ticket YAMLs for edge-candidate-agent export/validation.

Configure, extend, or contribute to Hermes Agent.

Author in-repo SKILL.md: frontmatter, validator, structure.

Modify, debug, or extend the s6-overlay supervision tree inside the Hermes Agent Docker image — adding new services, debugging profile gateways, understanding the Architecture B main-program pattern.

Use when you want to auto-generate reusable skills from repeated workflows. Watches your Hermes sessions, detects patterns, and proposes SKILL.md + plugin.py pairs on demand.

Use when a Hermes Kanban worker wants to run Codex CLI as an isolated implementation lane while Hermes keeps ownership of task lifecycle, reconciliation, testing, and handoff.

Decomposition playbook + anti-temptation rules for an orchestrator profile routing work through Kanban. The "don't do the work yourself" rule and the basic lifecycle are auto-injected into every kanban worker's system prompt; this skill is the deeper playbook when you're specifically playing the orchestrator role.

Pitfalls, examples, and edge cases for Hermes Kanban workers. The lifecycle itself is auto-injected into every worker's system prompt as KANBAN_GUIDANCE (from agent/prompt_builder.py); this skill is what you load when you want deeper detail on specific scenarios.

Use when orchestrating multi-agent workflows: deep research, planning with consensus, verified execution, triage, or autopilot. Suite of driver skills for Hermes-native multi-agent coordination.