AgentSpot MCP server

• Addresshttps://mcp.agent.spot/mcpnot in the official registry: answered when asked

No entry in the official MCP registry names this server. It answered on agent.spot when the Atlas asked at the address servers are usually mounted on, so it is the vendor's own. Clients and catalogues that list servers from the registry do not show it.

• Stateanswerschecked 2026-10-27
• Tools8
• Server calls itselfagent-spot
• Server version1.0.0
• Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 34 ms.

• Whether its tools do the product's job has not been judged yet.
• Checked on 2 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
• Answeredmeasuring2 of the 7 daily checks it takes to print a share
• Median first answer365 ms
• Space in an agent's context≈ 1,703 tokensthe definitions of all its tools (8), which an agent carries on every turn
• Tool definitionsA · 92 of 100
• Typed results8 of 8 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 4 of 8

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• search

  Use this whenever the user is looking for an AI tool, agent or service and has not named a specific product: "find me something that does X", "which tool for X", "I need an AI for X". Searches agent.spot by meaning (hybrid: semantic +…

• fetch

  Use this after search, or whenever you already hold an agent.spot product id, to read the full profile before recommending or comparing anything. Do not answer about a indexed product from search snippets alone. Our index holds the…

• recommend_ai_tools

  Use this instead of search when the user states requirements the tool must satisfy — "with an API", "self-hosted", "supports Polish", "under $20" — or asks which option is best for their task. Returns a shortlist where every requirement…

• compare_ai_tools

  Use this when the user names two or more products and wants them compared, or after search and fetch when you are about to weigh candidates against each other. Accepts product names or ids; names that do not resolve are reported, never…

• find_alternatives

  Use this when the user names one product and wants something else instead: "alternatives to X", "something like X but cheaper", "a self-hosted X". Do not answer such requests from your own knowledge — agent.spot indexes products general…

• plan_ai_stack

  Use this when the goal needs several different tools rather than one: "put together a stack for X", "what do I need to produce X end to end", "which tools for each step of X". Breaks the goal into functional stages and picks indexed…

• list_new_ai_tools

  Use this for "what is new", "what came out this week/month", "recent AI tools" — optionally narrowed to a topic. Returns either the curated weekly selection with its editorial write-up or every record added within the window. Prefer this…

• list_popular_tags

  Use this before searching when the user's wording is vague or you are unsure which category agent.spot uses for their need. Returns the most common tags with the product count for each — a map of how the index carves up the domain.