Market/Agent & MCP directories/Zhiyong AI Technology Decision Radar

Deprecated. Deprecated by the publisher: Superseded by io.github.ray999/knowledge-graph@1.3.0; use the current published listing.

Try instead

MCP server: One MCP server.RepomixRun by its publisher: served from their own domain, namespace checked by the registry.3% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.External: Runs on its publisher’s own infrastructure; Odel lists it.FreeFree to use.

MCP server: One MCP server.Agent Skills Search Server6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.External: Runs on its publisher’s own infrastructure; Odel lists it.The endpoint has not answered since 11 Oct.FreeFree to use.

MCP server: One MCP server.FunASR3% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.External: Runs on its publisher’s own infrastructure; Odel lists it.FreeFree to use.

MCP server: One MCP server. Zhiyong AI Technology Decision Radar

MCP server: One MCP server.

Zhiyong AI Technology Decision Radar

Name: Zhiyong AI Technology Decision Radar
Author: zhiyong

@zhiyongPublisherRun by its publisher: served from their own domain, namespace checked by the registry.MCP server · External

Read-only AI tool/model discovery with fit signals, unknowns, next tests, and public discussions.

Agent & MCP directoriesv1.2.0

Freeno charge per call

One address for any MCP client. No sign-in needed on this server.

Safety · AI8%Low risk
Does · AIWrites7 read · 4 act, by tool name
ConnectRemote · no sign-inStreamable HTTP
PopularityNo stars yetUpdated 6 Sep 2026
StatusDeprecatedAnswered Odel on 1 Oct

Overview Tools11 Trust Requirements Details Similar

What it does

7 read4 act

Grouped by tool name. At most: creates or changes data: records, files, settings.

What it costs

Free

Odel charges nothing per call. The publisher may charge for its own service.

Tools

11 · grouped by tool name · checked 1 Oct 2026

Read · 7Look things up

get_agent_task
list_feedback
get_popular_feedback
list_topics
search_knowledge_graph
get_knowledge_entity
compare_knowledge_entities

Act · 4Change something

submit_agent_observation
submit_agent_feedback
reply_to_feedback
create_topic

Try it in the Inspector

No README yet. What Odel knows about this module is on the right.

Checked by Odel

Endpoint answered on 1 Oct 2026
Registry verified the namespace dev.zhiyong
Endpoint is on the publisher's own domain
Deprecated by the publisher: Superseded by io.github.ray999/knowledge-graph@1.3.0; use the current published listing.

Assessed by AIJev

Harmful: 8%
First-party: 98%
High impact: 2%
Adult content: 1%

Read from the listing, its tools and README on 4 Oct 2026. AI can make mistakes: a guide, not a check.

Requirements

Runs: Remote, on zhiyong.dev
Transport: Streamable HTTP
Sign-in: None
Credentials: None asked
Clients: Any MCP client

https://zhiyong.dev/mcp

The publisher’s server itself; Odel doesn’t run it. Added to your modules, Odel fronts it with one address.

Details

Version: 1.2.0
Updated: 6 Sep 2026
Registry name: dev.zhiyong/knowledge-graph

kg.zhiyong.dev
Registry listing

Similar modules

Browse Agent & MCP directories

MCP server: One MCP server.
RepomixRun by its publisher: served from their own domain, namespace checked by the registry.
@yamadashy · External28,802 GitHub stars.
Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search
3% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
3% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
3% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Agent Skills Search Server
@mcp · External26,028 GitHub stars.
Search and discover Agent Skills from the skills.sh registry. Powered by HAPI MCP server.
6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.The endpoint has not answered since 11 Oct.Free to use.
6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.The endpoint has not answered since 11 Oct.Free to use.
6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.The endpoint has not answered since 11 Oct.Free to use.
MCP server: One MCP server.
FunASR
@modelscope · External20,637 GitHub stars.
Transcribe local audio with FunASR and SenseVoice using private, on-device inference.
3% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.Free to use.
3% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.Free to use.
3% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.Free to use.
MCP server: One MCP server.
MCP Registry Server
@mcp · External7,346 GitHub stars.
Publish and discover MCP servers via the official MCP Registry. Powered by HAPI MCP server.
4% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
4% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
4% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
FirebaseRun by its publisher: served from their own domain, namespace checked by the registry.
@firebase · External4,471 GitHub stars.
Gives AI development tools Firebase-specific capabilities and expertise.
3% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
3% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
3% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
AdsAgent
@nowork-studio · External3,911 GitHub stars.
Google Ads analysis and operations — read performance, manage keywords, bids, and campaigns.
Not assessed yet.What it can do is not assessed yet.A remote server; you sign in with your account.Deprecated by the publisher: Renamed to io.github.nowork-studio/notfair. Endpoint moved from adsagent.org/api/mcp to notfair.co/api/mcp; auth migrated from API key to OAuth 2.1.Free to use.
Not assessed yet.What it can do is not assessed yet.A remote server; you sign in with your account.Deprecated by the publisher: Renamed to io.github.nowork-studio/notfair. Endpoint moved from adsagent.org/api/mcp to notfair.co/api/mcp; auth migrated from API key to OAuth 2.1.Free to use.
Not assessed yet.What it can do is not assessed yet.A remote server; you sign in with your account.Deprecated by the publisher: Renamed to io.github.nowork-studio/notfair. Endpoint moved from adsagent.org/api/mcp to notfair.co/api/mcp; auth migrated from API key to OAuth 2.1.Free to use.
MCP server: One MCP server.
NotFair-MetaAds
@nowork-studio · External3,911 GitHub stars.
Meta Ads MCP (Facebook + Instagram) - analyze performance, manage budgets, pause campaigns.
Not assessed yet.What it can do is not assessed yet.A remote server; you sign in with your account.Deprecated by the publisher: Superseded by io.github.nowork-studio/notfair, which covers Meta Ads and every other NotFair platform at https://notfair.co/api/mcp/notfair. This endpoint keeps working for existing connections.Free to use.
Not assessed yet.What it can do is not assessed yet.A remote server; you sign in with your account.Deprecated by the publisher: Superseded by io.github.nowork-studio/notfair, which covers Meta Ads and every other NotFair platform at https://notfair.co/api/mcp/notfair. This endpoint keeps working for existing connections.Free to use.
Not assessed yet.What it can do is not assessed yet.A remote server; you sign in with your account.Deprecated by the publisher: Superseded by io.github.nowork-studio/notfair, which covers Meta Ads and every other NotFair platform at https://notfair.co/api/mcp/notfair. This endpoint keeps working for existing connections.Free to use.
MCP server: One MCP server.
VexaRun by its publisher: served from their own domain, namespace checked by the registry.
@vexa · External2,869 GitHub stars.
Meeting bot and transcripts for Google Meet, Teams and Zoom. Live or after, speakers labelled.
6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; it needs your API key.Free to use.
6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; it needs your API key.Free to use.
6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; it needs your API key.Free to use.

MCP server: One MCP server.
Zhiyong Parcel Tracking
@zhiyong · External
General parcel tracking; currently supports UniUni, with more carriers planned.
7% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
7% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
7% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Shiftly Staff Scheduling DemoRun by its publisher: served from their own domain, namespace checked by the registry.
@zhiyong · External
Free no-account staff scheduling demo: fictional data, unsaved drafts, no real-store access.
6% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
6% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
6% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.