Agent Media Toolkit MCP
A hosted MCP server providing 15 media and data tools for AI agents, including web search, news, transcription, subtitles, voiceover, translation, summarization, moderation, and short-form video editing. It operates on a freemium model where lighter tools are free over MCP, while premium media tools are pay-per-call via x402.
Endpoint and access
No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.
https://podcast-shorts-a2a-production.up.railway.app/mcp/What its tools do
15 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.
Checks and signals
Each line is separate evidence, not a trust score.
- Passed Endpoint answered the live check ·
- Availability 1 of 1 checks passed in 30 days
What you can do with it
- Perform live web search and retrieve recent news
- Transcribe audio/video files and generate subtitles
- Translate text into various languages
- Generate voiceovers from text input
Source and maintenance
- Maintenance checked
Protocol and capabilities
- Server
- Agent Media Toolkit 1.28.1
- MCP protocol negotiated in check
- 2025-11-25
- Tools
- 15 advertised
- Resources
- 0 advertised
- Resource templates
- 0 advertised
- Prompts
- 0 advertised
{
"tools": {
"listChanged": false
},
"prompts": {
"listChanged": false
},
"resources": {
"subscribe": false,
"listChanged": false
},
"experimental": {}
}Tools
15 advertised
search
Live web search. Returns results with title, url, and snippet.
{
"type": "object",
"title": "searchArguments",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"title": "Query"
},
"max_results": {
"type": "integer",
"title": "Max Results",
"default": 5
}
}
}news
Recent news for a query/niche. Returns items with title, url, snippet, date, source.
{
"type": "object",
"title": "newsArguments",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"title": "Query"
},
"max_results": {
"type": "integer",
"title": "Max Results",
"default": 6
}
}
}extract
Fetch a web page and return clean main-content text (no nav/ads/boilerplate).
{
"type": "object",
"title": "extractArguments",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"title": "Url"
},
"max_chars": {
"type": "integer",
"title": "Max Chars",
"default": 20000
}
}
}summarize
Summarize text OR a web page (give text or url). style: paragraph|bullets.
{
"type": "object",
"title": "summarizeArguments",
"properties": {
"url": {
"type": "string",
"title": "Url",
"default": ""
},
"text": {
"type": "string",
"title": "Text",
"default": ""
},
"style": {
"type": "string",
"title": "Style",
"default": "paragraph"
},
"max_words": {
"type": "integer",
"title": "Max Words",
"default": 120
}
}
}repurpose
Turn text into social assets: thread, summary, titles, hashtags.
{
"type": "object",
"title": "repurposeArguments",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"title": "Text"
},
"niche": {
"type": "string",
"title": "Niche",
"default": ""
},
"formats": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "null"
}
],
"title": "Formats",
"default": null
}
}
}translate
Translate text into target_lang (e.g. 'Spanish', 'ja').
{
"type": "object",
"title": "translateArguments",
"required": [
"text",
"target_lang"
],
"properties": {
"text": {
"type": "string",
"title": "Text"
},
"source_lang": {
"type": "string",
"title": "Source Lang",
"default": ""
},
"target_lang": {
"type": "string",
"title": "Target Lang"
}
}
}script
Write a short-form video script (hook, beats, cta) for a topic.
{
"type": "object",
"title": "scriptArguments",
"required": [
"topic"
],
"properties": {
"tone": {
"type": "string",
"title": "Tone",
"default": ""
},
"topic": {
"type": "string",
"title": "Topic"
},
"platform": {
"type": "string",
"title": "Platform",
"default": "shorts"
},
"duration_s": {
"type": "integer",
"title": "Duration S",
"default": 45
}
}
}moderate
Content-safety classification: flagged?, categories, severity, reason.
{
"type": "object",
"title": "moderateArguments",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"title": "Text"
}
}
}media_info
Metadata (title, duration, uploader, views) for a media URL — no download.
{
"type": "object",
"title": "media_infoArguments",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"title": "Url"
}
}
}voiceover
Text -> natural MP3 narration. Returns a download URL.
{
"type": "object",
"title": "voiceoverArguments",
"required": [
"text"
],
"properties": {
"rate": {
"type": "string",
"title": "Rate",
"default": "+0%"
},
"text": {
"type": "string",
"title": "Text"
},
"voice": {
"type": "string",
"title": "Voice",
"default": "en-US-ChristopherNeural"
}
}
}package_post
Platform-optimized title, description, and hashtags for a clip. Premium (via x402).
{
"type": "object",
"title": "package_postArguments",
"required": [
"transcript_excerpt"
],
"properties": {
"niche": {
"type": "string",
"title": "Niche",
"default": ""
},
"platforms": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "null"
}
],
"title": "Platforms",
"default": null
},
"transcript_excerpt": {
"type": "string",
"title": "Transcript Excerpt"
}
}
}transcribe
Transcribe an audio/video URL to timestamped text. Premium (via x402).
{
"type": "object",
"title": "transcribeArguments",
"required": [
"source_url"
],
"properties": {
"source_url": {
"type": "string",
"title": "Source Url"
}
}
}subtitles
Audio/video URL -> .srt/.vtt subtitle file. Premium (via x402).
{
"type": "object",
"title": "subtitlesArguments",
"required": [
"source_url"
],
"properties": {
"format": {
"type": "string",
"title": "Format",
"default": "srt"
},
"source_url": {
"type": "string",
"title": "Source Url"
}
}
}find_clips
Find viral clip candidates in a long video with scores. Premium (via x402).
{
"type": "object",
"title": "find_clipsArguments",
"required": [
"source_url"
],
"properties": {
"niche": {
"type": "string",
"title": "Niche",
"default": ""
},
"max_clips": {
"type": "integer",
"title": "Max Clips",
"default": 5
},
"source_url": {
"type": "string",
"title": "Source Url"
}
}
}edit_clip
Cut a time range into a finished 9:16 captioned short. Premium (via x402).
{
"type": "object",
"title": "edit_clipArguments",
"required": [
"source_url",
"start_s",
"end_s"
],
"properties": {
"end_s": {
"type": "number",
"title": "End S"
},
"style": {
"type": "string",
"title": "Style",
"default": "bold-captions"
},
"start_s": {
"type": "number",
"title": "Start S"
},
"source_url": {
"type": "string",
"title": "Source Url"
}
}
}Prompts
0 advertised
Resources
0 advertised
90-day uptime
A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.
- 2026-11-06: 1 of 1 checks answered
30-day availability
Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.
- Successful checks
- 1 of 1 (100%)
- Average latency
- 1665 ms
- 95th percentile latency
- 1665 ms
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · probe · passed · 1665 ms · metadata changed · 15 tool(s), 0 resource(s), 0 resource template(s), 0 prompt(s)
Connect from your client
Each snippet registers the same endpoint; pick the client you use.
Claude Code
claude mcp add --transport http agent-media-toolkit-mcp https://podcast-shorts-a2a-production.up.railway.app/mcp/Codex
codex mcp add agent-media-toolkit-mcp --url https://podcast-shorts-a2a-production.up.railway.app/mcp/Cursor
{
"mcpServers": {
"agent-media-toolkit-mcp": {
"url": "https://podcast-shorts-a2a-production.up.railway.app/mcp/"
}
}
}Cline
{
"mcpServers": {
"agent-media-toolkit-mcp": {
"type": "streamableHttp",
"url": "https://podcast-shorts-a2a-production.up.railway.app/mcp/",
"disabled": false
}
}
}VS Code
{
"servers": {
"agent-media-toolkit-mcp": {
"type": "http",
"url": "https://podcast-shorts-a2a-production.up.railway.app/mcp/"
}
}
}Gemini CLI
gemini mcp add --transport http agent-media-toolkit-mcp https://podcast-shorts-a2a-production.up.railway.app/mcp/Claude Desktop
https://podcast-shorts-a2a-production.up.railway.app/mcp/Windsurf
{
"mcpServers": {
"agent-media-toolkit-mcp": {
"serverUrl": "https://podcast-shorts-a2a-production.up.railway.app/mcp/"
}
}
}Let your agent find its tools
Find servers like Agent Media Toolkit MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.