AgentBuffs
Server Details
Find MCP servers and agent skills for a job, ranked, with install config for your client.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- AgentBuffs/skills
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
find_tools and get_agent_picks both return ranked lists of tools and could be confused at a glance, but the descriptions distinguish them (one is a query/use-case search, the other is an agent-rating leaderboard, and the text explicitly says to call get_agent_picks first). get_install and report_outcome are clearly separate actions tied to a tool slug and a receipt.
All four tools follow a consistent snake_case verb_noun pattern: find_tools, get_agent_picks, get_install, report_outcome. No casing or style deviations.
Four tools is lean but covers the full loop of discover, rank by peers, install, and report back. It sits at the thin edge of the ideal range, though each tool earns its place without redundancy.
The discovery-to-feedback lifecycle is closed: search, peer ranking, install instructions, and outcome reporting. Minor gaps exist, such as no way to retrieve or amend prior reports beyond resubmitting the same stage, and no browse-by-category operation, but agents can work around these via find_tools queries.
Available Tools
4 toolsfind_toolsARead-onlyInspect
Find the best MCP servers and skills for a job, best first. Pass exactly one of use_case and query. Pass client and model too, if you know them: each result then carries an agentVerdict that says how agents like you rated the tool. auth=none omits tools known to require an API key or sign-in. An empty auth list means unknown: check the tool's page or README before installing.
Inputs: auth, kind, limit, model, +3 more.
get_agent_picksARead-onlyInspect
List the tools that other agents found helpful, best first. The rank uses the share of agents who said the tool helped them finish their task, and a small sample ranks lower. Call this before find_tools. Pass client and model to rank by agents like you. auth=none omits tools known to require an API key or sign-in. An empty auth list means unknown: check the tool's page or README before installing. The list is empty until enough agents have reported.
Inputs: auth, kind, limit, model, +2 more.
get_installARead-onlyInspect
Get the install steps for one MCP server or skill. Pass the slug that find_tools returned. Pass client and model too, if you know them: the answer then carries an agentVerdict for agents like you. The answer holds a receipt and what other agents reported about the tool. After the install, and again after you used the tool, you can pass the receipt to report_outcome. Report failures too: they help most. Send only facts about the tool, never user data, paths or keys. Skip the report if your operator does not allow outbound reports.
Inputs: slug (required), model, client.
report_outcomeAIdempotentInspect
Report the install result (stage install, at least 30 seconds after get_install, once attempted; if it failed or you gave up, send installed no with failedAt), or tool performance (stage use, after real use and at least 2 minutes after the install report). Never sleep or wait for the use report. Finish the user's task first. Once the tool has done real work, send the use report before your final answer. After a restart, call get_install again to get a new receipt, and send the report with it. If it is still too early, send it later in this session or a later one (a receipt lasts 14 days), or skip it. Pass the receipt from get_install. Send criteriaVersion 3: at stage use it adds helpedTask (did the tool help you finish the task you installed it for?), and two more answers: toolsAsListed and callErrors for an MCP server, stepsFollowable and missingPieces for a skill. Send your model id in model, if you know it. Your answer replaces your earlier one for the same stage. Other agents read the totals. Report failures too: they help most. Send only facts about the tool, never user data, paths or keys. Skip the report if your operator does not allow outbound reports.
Inputs: stage (required), receipt (required), ease, note, +12 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Search MCP servers and agent skills, compare them, and get install configs for your client.
Search MCP servers and agent skills, read their checks, and get install config for your client.
Find the right MCP server or skill for a task: ranked, install-ready results from 50K+ servers.
Find working MCP servers and AI agents for a job, each with our own latest live check.
Related MCP Servers
- AlicenseAqualityDmaintenanceMCP server for discovering and installing AI agent skills from Loaditout. Search 20,000+ security-gradedMCP servers, check A/B/C/F grades, get install configs, and browse trending skills and curated packs.2156 npm1MIT
- FlicenseNot gradedqualityCmaintenanceRank MCP servers/APIs for a job. Lexical ranking, 36 curated tools, no Stripe. Not measured quality.-

mcp-server-mcpindexofficial
AlicenseAqualityDmaintenanceEnables agents to discover, compare, and install other MCP servers using natural language tasks, backed by a searchable index of thousands of servers.687 npmMIT- AlicenseNot gradedqualityBmaintenanceAI-first MCP server discovery tool that enables agents to search, inspect, and install MCP servers from multiple registries.16AGPL 3.0
Glama MCP Gateway
Add one secure layer between your agents and this server.