Find MCP servers and agent skills for a job, ranked, with install config for your client.
Scored across 2 tools
find_tools is a search/discovery operation while get_install retrieves install instructions for a specific slug returned by find_tools. The two purposes are clearly distinct, and get_install's description explicitly chains off find_tools output, eliminating misselection risk.
Both names follow a clean verb_noun snake_case pattern (find_tools, get_install). No mixing of conventions or vague verbs.
Only two tools, which is on the thin side even for a narrow discovery-and-install purpose. A browse/list or detail-inspection tool would round out the surface without bloat.
The core lifecycle (discover a server/skill, then get its install steps) is covered end to end. Minor gaps exist, such as no way to list or browse all entries or fetch richer metadata like descriptions or ratings before installing.
Find the best MCP servers and skills for a job, best first. Pass exactly one of use_case and query.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | Only MCP servers (mcp) or only skills (skill). Leave it out for both. | |
| limit | No | How many results to return, 1 to 25. The default is 10. | |
| query | No | Free text search of 2 to 100 characters. Use it when no use case fits. | |
| client | No | Only tools this client can run, for example claude-code or cursor. | |
| use_case | No | The job to do. Pick one slug from the list. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover safety (readOnlyHint) and scope (openWorldHint=false). The description usefully adds the result ordering ("best first"), but says nothing about what a result contains or how ranking is determined.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with zero waste; the core purpose and the hard constraint are both front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
All five parameters are fully documented and the constraint is stated, with no output schema to explain. The only remaining gap is result shape and ranking semantics, which matters somewhat for a discovery tool but is a minor omission.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3, and the description adds the mutual-exclusion contract between use_case and query that the schema only hints at. It adds no further meaning for kind, limit, or client, which the schema already documents well.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource: ranking MCP servers and skills for a job, with an explicit ordering ("best first"). It is clearly distinct from the only sibling, get_install, but the description never names that distinction explicitly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
"Pass exactly one of use_case and query" is an explicit, actionable selection rule that an agent could easily get wrong otherwise. It still leaves the tool-vs-sibling routing (search here, install there) to inference from the names.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the install steps for one MCP server or skill. Pass the slug that find_tools returned.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | The slug of the tool. | |
| client | No | Only the install steps for this client. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safe read profile is covered. The description is consistent with that but adds nothing further: it does not say what the steps look like, whether the optional client filter narrows output, or how an unknown slug is handled. Adequate against a lower annotation-era bar, not more.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences, zero filler, with the action leading and the parameter instruction following. Every clause earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple two-parameter read lookup with full schema coverage and annotations covering safety, the description is nearly sufficient. The only genuine gap is the unmentioned client parameter that lets an agent narrow output to one environment.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so both parameters are already documented in the schema. The description adds real value on half of that surface by stating the slug's provenance ('that find_tools returned'), but it never mentions the optional client parameter or its role in scoping results. Baseline 3 is correct.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Get the install steps') plus an explicit scope of one item ('one MCP server or skill'), and names the sibling find_tools as the source of the slug. An agent can select this over find_tools without opening either schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Establishes the prerequisite workflow directly: the slug must come from find_tools, which routes the agent to the correct ordering of the two sibling tools. No explicit when-not-to-use or exclusion is given, but the context is unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
find_toolsget_installAgent-first search of MCP servers, APIs, CLIs and skills, with best picks and transparent scores.
Find MCP servers & agents for any task. Paid, charged only on delivery: live-verified matches.
Find MCP servers, skills, plugins, agents, prompts and rules for any task.
Add one secure layer between your agents and this server.
