New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Hydra MCP

by streamband in streamband/hydra-srt

Query the running HydraSRT instance via MCP (routes, logs, stats, control).

Apache-2.0Auto-check passedAgent Workflows

Install Hydra MCP

skills CLI
$ npx skills add streamband/hydra-srt --skill hydra-mcp -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install streamband/hydra-srt hydra-mcp --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/streamband/hydra-srt.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/hydra-mcp .claude/skills/hydra-mcp && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
hydra-mcp
GitHub stars
147
Token cost
~789 tokens
SKILL.md length
349 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
Apache-2.0

At a glance

Query the running HydraSRT instance via MCP (routes, logs, stats, control).

  • Works in 6 steps: Read tool schemas first — inspect… → Prefer MCP over guessing — use MCP tools… → Pick the smallest set of tools — e.g.… → …
  • The user invokes /HydraSRT
  • SKILL.md covers User request, MCP server, How to work and Tool domains (43 tools), plus 2 more sections
  • Calls make

What it does

Hydra MCP is an agent skill from streamband/hydra-srt. Query the running HydraSRT instance via MCP (routes, logs, stats, control). Use when the user invokes /HydraSRT or asks to inspect or control a live HydraSRT deployment through MCP.

Its SKILL.md is about 790 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol. The repository describes itself as: An Open Source Alternative to Haivision SRT Gateway. The licence is Apache-2.0.

When your agent uses it

  • The user invokes /HydraSRT
  • Asks to inspect
  • Control a live HydraSRT deployment through MCP

Example prompts

  • “/hydra-mcp”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Read tool schemas first — inspect available MCP tool descriptors before calling.
  2. Prefer MCP over guessing — use MCP tools for routes, sources, destinations, tags, interfaces, nodes, analytics, and logs. Do not invent…
  3. Pick the smallest set of tools — e.g. list_routes before get_route; use filters and time ranges instead of dumping everything.
  4. Mutations need confirmation — before create_*, update_*, delete_*, start_route, stop_route, restart_route, or switch_route_source…
  5. Time ranges — analytics/log tools accept window: last_30_min, last_hour, last_6_hour, last_24_hour, or custom from + to (ISO8601). window…
  6. Scoped IDs — source and destination tools require route_id in addition to entity IDs.

What it can do on your machine

Read from SKILL.md and the folder at commit 8d081f2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • make

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Hydra MCP loads about 789 tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 349 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~48
When it runs · the whole SKILL.md, loaded when a task matches
~789

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from streamband/hydra-srt at commit 8d081f2, republished under its Apache-2.0 licence (© streamband). 349 words, ~789 tokens.

Download SKILL.mdSave it as .claude/skills/hydra-mcp/SKILL.md (or your agent's skills folder).
name
hydra-mcp
description
Query the running HydraSRT instance via MCP (routes, logs, stats, control). Use when the user invokes /HydraSRT or asks to inspect or control a live HydraSRT deployment through MCP.
disable-model-invocation
true

HydraSRT MCP

Operate against a live HydraSRT instance through its MCP server.

User request

The user invoked /HydraSRT (or an equivalent slash command) and their question follows in the same message. Treat that text as the task to complete.

MCP server

  • Endpoint: http://localhost:4000/mcp (adjust host/port to the running instance)
  • Auth: Authorization: Bearer <MCP token> — dedicated MCP token from Settings → MCP tokens (not the UI session token)
  • Prerequisite: HydraSRT must be running (make dev or equivalent). If MCP is unavailable, say so and ask the user to start Hydra and verify MCP client configuration.

How to work

  1. Read tool schemas first — inspect available MCP tool descriptors before calling.
  2. Prefer MCP over guessing — use MCP tools for routes, sources, destinations, tags, interfaces, nodes, analytics, and logs. Do not invent IDs or statuses.
  3. Pick the smallest set of tools — e.g. list_routes before get_route; use filters and time ranges instead of dumping everything.
  4. Mutations need confirmation — before create_*, update_*, delete_*, start_route, stop_route, restart_route, or switch_route_source, summarize the planned change and ask unless the user already asked for that exact action.
  5. Time ranges — analytics/log tools accept window: last_30_min, last_hour, last_6_hour, last_24_hour, or custom from + to (ISO8601). window: live is not supported; use explicit from/to for polling.
  6. Scoped IDs — source and destination tools require route_id in addition to entity IDs.

Tool domains (43 tools)

DomainExamples
Routeslist_routes, get_route, start_route, stop_route, restart_route, switch_route_source
Sourceslist_sources, get_source, test_source (requires route_id)
Destinationslist_destinations, get_destination (requires route_id)
Tagslist_tags, create_tag, update_tag, delete_tag
Interfaceslist_interfaces, list_system_interfaces, get_system_interface
Nodeslist_nodes, get_self_node, get_node_analytics
Observabilityget_route_events, get_route_pipeline_logs, get_route_analytics, get_routes_status_history

Full catalog and contracts: docs/mcp.md.

Response format

  • Lead with a direct answer to the user's question.
  • Cite concrete data from MCP responses (route names/IDs, statuses, counts, recent log lines).
  • If a tool returns {"error": ...} or {"errors": ...}, explain it plainly and suggest the next step.
  • Keep output concise unless the user asked for a full dump.

Out of scope for MCP

MCP token CRUD, backup/restore, WebSocket live push, and UI login stay on REST/UI only. Point the user to the web UI or docs/api.md if they need those.

© streamband, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/hydra-mcp of streamband/hydra-srt.

Open the folder on GitHubat commit 8d081f2

Compare with similar skills

Hydra MCP next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Hydra MCP compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hydra MCP this skillstreamband/hydra-srt147—~789Automated safety check: PassApache-2.0
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official38k11 repos~3.1kAutomated safety check: PassApache-2.0
Crush Configurationcharmbracelet/crush29k—~3.7kAutomated safety check: PassCustom licence
Context Mode Output Sandboxmksglu/context-mode26k—~4.1kAutomated safety check: PassCustom licence

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed

  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Context Mode Output Sandbox

    mksglu/context-mode

    Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.

    26k GitHub stars~4.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Warp GUI to Agent CLI Migration

    warpdotdev/warp

    Migrates the compatible subset of settings and global file-based MCP servers from the Warp desktop app into Warp Agent CLI without exposing credentials or state.

    65k GitHub starsUsed in 1 repo~2.1k tokens
    Agent WorkflowsAuto-check passed

More from streamband/hydra-srt

  • Elixir

    streamband/hydra-srt

    A skill your agent uses for Elixir/Phoenix development in this repo: implementing features, refactors, debugging, tests, Ecto changes, and production-safe fixes.

    147 GitHub stars~804 tokensUpdated 23 days ago
    Auto-check passed

  • Hydra Dev

    streamband/hydra-srt

    Run HydraSRT development workflows: mix q quality gate, Elixir unit/E2E tests, native Rust tests, web Vitest/Playwright, and make dev.

    147 GitHub stars~995 tokensUpdated 23 days ago
    Auto-check passed

  • Frontend

    streamband/hydra-srt

    A skill your agent uses for frontend work in webapp (React/TypeScript, UI implementation, tests, and refactors).

    147 GitHub stars~582 tokensUpdated 23 days ago
    Auto-check passed

  • Gstreamer

    streamband/hydra-srt

    A skill your agent uses for GStreamer pipeline development and debugging: graph design, caps negotiation issues, latency, synchronization, and runtime diagnostics.

    147 GitHub stars~499 tokensUpdated 23 days ago
    Auto-check passed

  • Hydra Architect

    streamband/hydra-srt

    A skill your agent uses when designing or evolving Hydra platform architecture across Elixir/Phoenix, SQLite, VictoriaMetrics/VictoriaLogs analytics, native/Rust, and runtime boundaries.

    147 GitHub stars~1.2k tokensUpdated 23 days ago
    Auto-check passed

  • Rust

    streamband/hydra-srt

    A skill your agent uses for Rust development in this repo: design, implementation, debugging, performance work, and reliable testing.

    147 GitHub stars~459 tokensUpdated 23 days ago
    Auto-check passed

Works with

Categories

Questions about Hydra MCP

What does Hydra MCP do?

Query the running HydraSRT instance via MCP (routes, logs, stats, control). Hydra MCP is an agent skill from streamband/hydra-srt. Query the running HydraSRT instance via MCP (routes, logs, stats, control).

When should I use Hydra MCP?

Hydra MCP fits situations like: the user invokes /HydraSRT; asks to inspect; control a live HydraSRT deployment through MCP.

How do I install Hydra MCP in Claude Code?

Run `npx skills add streamband/hydra-srt --skill hydra-mcp -a claude-code`. Or copy the skill folder (.agents/skills/hydra-mcp in streamband/hydra-srt) into .claude/skills/hydra-mcp in your project. Claude Code loads it when a task matches its description.

How do I install Hydra MCP in Codex?

Run `npx skills add streamband/hydra-srt --skill hydra-mcp -a codex`. Or copy the skill folder (.agents/skills/hydra-mcp in streamband/hydra-srt) into .agents/skills/hydra-mcp in your project. Codex loads it when a task matches its description.

Can I use Hydra MCP in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add streamband/hydra-srt --skill hydra-mcp -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hydra-mcp, .gemini/skills/hydra-mcp, .github/skills/hydra-mcp and .opencode/skills/hydra-mcp in your project.

What does Hydra MCP need to run?

Going by SKILL.md and its folder, Hydra MCP needs the command-line tools its instructions call (make).

Does Hydra MCP access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Hydra MCP safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Hydra MCP use?

Hydra MCP is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Hydra MCP use?

About 789 tokens (SKILL.md is roughly 3.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Hydra MCP?

Skills that share tags, products or a category with Hydra MCP: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Crush Configuration (charmbracelet/crush, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hydra MCP?

streamband (a GitHub organization) maintains it in streamband/hydra-srt, which has 147 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on September 16, 2026.

Source: streamband/hydra-srt on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.