FindAgent

findagent_create_draft

Persist a DRAFT marketplace listing you wrote (from import_repo grounding). Creates a status=draft agent owned by you; then call findagent_submit_for_review IN THIS MCP CLIENT to set price + confirm originality/prohibited + submit it — the web is only an optional preview, not where you finish. Prefer findagent_submission_wizard to collect all of these fields step-by-step (one selectable question at a time) before calling this. Before calling: use findagent_check_slug to confirm the slug is free, and findagent_list_categories to pick the primary (top-level) category + a discipline. NEVER send secret credential VALUES — credential_slots declare the shape (ref/label/allowed_hosts/type) only.

Input Schema

TableJSON Schema

Name	Required	Description
`kind`	No	Optional — usually INFERRED from whether you pass `tools` (tools present → 'mcp-tool' doer, else 'static-recipe' recipe). Declared so a manifest-shaped payload is accepted, not rejected.
`llms`	No	Optional target clients. Defaults to ['claude','chatgpt','gemini'] when omitted.
`slug`	No	Permanent URL slug, kebab-case (3–60, no leading/trailing hyphen). Verify with findagent_check_slug first.
`tags`	No	Optional (≤10). Free-form lowercase tags ([a-z0-9- ]).
`title`	No	Agent name (3–80 chars). Alias accepted: `name`.
`tools`	No	Optional doer tools (full web-builder parity). Omit for a recipe agent. Each item's shape is defined in `items` — name/description/tool_type/action are the load-bearing fields; auth_ref must match a credential_slots[].ref whose allowed_hosts cover the action host (audience binding — enforced).
`tagline`	No	One-line value prop (10–140).
`version`	No	Optional semver release version for this listing (e.g. "1.0.0"). Self-described metadata only — the platform tracks the authoritative version separately.
`metadata`	No	Optional professional listing metadata. { license?, homepage?, docs_url?, support_url?, support_email?, icon?, author?:{ name, url? }, maintainer?:{ name, url? } }. Every URL/icon must be https. An invalid block is dropped (not persisted).
`changelog`	No	Optional human release notes for `version` (max 10000 chars).
`languages`	No	Optional (≤20). Language/Framework slugs from findagent_list_tech_facets (software-development discipline only).
`guardrails`	No	Optional declared guardrails (doer agents). { input?: { max_length?, deny_patterns?:string[], pii_redaction?:string[] }, output?: { schema? }, actions?: { [toolName]: { approval?:"none"\|"human", max_amount?, rate_limit?:"10/hour", idempotent? } } }. You can only TIGHTEN — the platform always applies its mandatory rails. An invalid block fails the draft.
`price_type`	No	Optional, default free. "paid" requires price_cents (charged only once Paddle is live).
`description`	No	What it does / who it is for (50–4000).
`price_cents`	No	Required when price_type=paid: a positive integer of US cents, max 50000 ($500).
`tech_domains`	No	Optional (≤20). Tech Domain slugs from findagent_list_tech_facets (software-development discipline only).
`category_slug`	No	The PRIMARY category: a TOP-LEVEL slug from findagent_list_categories. Alias accepted: `category`. At least one of {category_slug, additional_category_slugs} MUST be a discipline (category_type='discipline'), AND for EVERY top-level you select you MUST also include one of its OWN subcategories in additional_category_slugs.
`system_prompt`	No	The agent instructions (50–20000 chars).
`example_prompts`	No	2–5 concrete asks (required).
`credential_slots`	No	Optional. Each item declares the SHAPE of a secret (ref/label/allowed_hosts/auth_scheme…) — see `items`. DEFINITIONS ONLY — never send secret VALUES.
`additional_category_slugs`	No	Optional (≤12). Extra slugs from findagent_list_categories. Include one subcategory under EVERY top-level you select (a subdiscipline under your discipline; a subindustry under any industry). Also where a discipline goes when the primary is an industry.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`slug`	No
`status`	No
`account`	No
`created`	No
`next_tool`	No
`preview_url`	No
`instructions`	No
`slug_is_permanent_after_publish`	No

TDQS

A5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses the persistence behavior ('status=draft agent owned by you') and the required follow-up workflow, which goes well beyond the annotations. It also adds behavioral nuances such as invalid metadata blocks being dropped, invalid guardrails failing the draft, and credential_slots being shape-only declarations. No contradiction with readOnlyHint=false or destructiveHint=false.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core purpose is front-loaded in the first sentence, and every subsequent sentence earns its place: sibling routing, preflight checks, follow-up steps, and a security warning. Despite its length, the density of actionable guidance is justified by the 21-parameter surface area.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description gives a complete operational context: where the draft comes from, which sibling tools to use before and after, how to structure credential declarations, and which preconditions to verify. Since an output schema exists, the description need not explain return values, and nothing needed for correct invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although schema coverage is 100% and the baseline is 3, the description adds crucial inter-parameter semantics: kind is inferred from tools, title accepts the alias name, credential_slots must not contain secret values, auth_ref must match allowed_hosts, and category selection has discipline/subcategory constraints. These relationships are not fully obvious from the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Persist a DRAFT marketplace listing' and 'Creates a status=draft agent owned by you.' It differentiates itself from siblings by explicitly naming findagent_submit_for_review and findagent_submission_wizard as separate steps/tools, so an agent can tell exactly what this tool alone accomplishes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit guidance is given: prefer findagent_submission_wizard first, use findagent_check_slug and findagent_list_categories before calling, then call findagent_submit_for_review in the MCP client. It also clarifies that the web is only an optional preview, not where completion happens, and states a hard security rule about never sending secret values.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All FindAgent tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0

Disambiguation5/5

Every tool targets a clearly scoped resource+action combination, and the versioning variants (bump_version vs repull vs reintrospect_mcp) are explicitly disambiguated by agent kind. Even with 52 tools, the descriptions make each purpose distinct enough to avoid misselection.

Naming Consistency4/5

Nearly all tools follow the findagent_<verb>_<object> snake_case pattern, and families share predictable verbs like list, create, delete, edit, and submit. Minor exceptions such as findagent_preflight, findagent_whoami, and findagent_earnings keep it from perfect consistency.

Tool Count2/5

At 52 tools, this far exceeds the 25-tool threshold for a coherent MCP surface. The count may reflect a broad platform, but as a single toolset it is heavy and likely to strain agent selection and context.

Completeness3/5

The surface covers publishing, versioning, knowledge bases, org management, GitHub import, purchases, and the demand board in impressive depth. However, there are notable dead ends: no unpublish/delete for a live agent, no request-fulfillment/linking action, and no org deletion or KB document update.

Resources

Need Help?