sella

browse_catalog

Read-only

Walk the API catalogue as a tree instead of a flat list. Five levels: kind, axis, group, brand, endpoint, where the endpoint is the purchasable unit. Call with no path for the root, then follow a child path. Every response returns breadcrumb, children with counts, the filters valid at that depth, and what to call next. Filters narrow the whole subtree below the current node. If you already know what you want, pass query to jump straight to the matching node in one call instead of walking down. Free and read-only.

Input Schema

TableJSON Schema

Name	Required	Description
`path`	No	Node to open, e.g. "" (root), "api", "api/by_function", "api/by_function/A7", "api/by_function/A7/exa", or a full endpoint path. Take these from the children of a previous call.
`chain`	No	Settlement chain, e.g. base, solana.
`limit`	No	Max children per page (1 to 50).
`query`	No	Jump to the node that best matches this text, skipping the walk. Ignored when path is set. Resolves to a brand when one matches, otherwise the closest domain group.
`offset`	No	Offset into the children for paging.
`free_only`	No	Only endpoints priced at zero.
`seller_type`	No	first_party is the brand serving its own endpoint; reseller and gateway are third parties charging for someone else's API.
`max_price_usdc`	No	Only endpoints at or under this USDC price.
`require_schema`	No	Only endpoints that publish an input schema. Use this when you intend to call the endpoint without a human reading its docs.
`include_unavailable`	No	Show endpoints a probe proved unreachable or unpayable. Off by default: those calls fail on the first request. Endpoints not yet probed are always shown, since unknown is not the same as broken.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed2 schema fields changedAug 9, 2026

removedInput schema / properties / exclude_unhealthy

Removed value: -{
-  "description": "Drop endpoints a probe has proven unpayable. Endpoints not yet probed are kept, not assumed good.",
-  "type": "boolean"
-}

addedInput schema / properties / include_unavailable

Added value: +{
+  "description": "Show endpoints a probe proved unreachable or unpayable. Off by default: those calls fail on the first request. Endpoints not yet probed are always shown, since unknown is not the same as broken.",
+  "type": "boolean"
+}

AddedAug 3, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations declare readOnlyHint=true, and the description reinforces this with 'Free and read-only'. It adds valuable behavioral context beyond annotations: 'Every response returns breadcrumb, children with counts, the filters valid at that depth, and what to call next' and 'Filters narrow the whole subtree below the current node.' This gives agents a clear model of the tool's behavior.

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 description is four dense sentences, front-loaded with the core purpose. Every sentence adds value (structure, usage, response behavior, shortcut), with no redundancy or fluff.

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

Completeness4/5

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

Despite having 10 parameters and no output schema, the description covers the key conceptual model (tree traversal), response contents, and filter semantics. It doesn't detail paging or specific filter parameters, but the schema descriptions already cover those, and the description provides sufficient context for an agent to use the tool correctly.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3. The description adds conceptual meaning by explaining how filters narrow the subtree and how query jumps to a node, which is not fully captured in individual parameter descriptions. This elevates the score to 4.

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 clearly states the tool's function: 'Walk the API catalogue as a tree instead of a flat list' and specifies the five levels ('kind, axis, group, brand, endpoint'). This distinguishes it from flat-list tools like search_catalog, making the purpose unambiguous.

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

Usage Guidelines4/5

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

The description gives concrete usage instructions: 'Call with no path for the root, then follow a child path' and explains when to use the query shortcut ('If you already know what you want, pass query to jump straight'). It implies alternatives (flat list) but does not explicitly name sibling tools, so it misses the top score.

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

All sella 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

A4/5.0

Disambiguation4/5

Most tools have clearly distinct purposes, but the deprecated tools (list_datasets, list_market_apis, search_datasets, try_dataset) overlap with modern replacements (search_catalog, get_listing). Some functional overlap exists between get_activity and charge_list, but descriptions clarify their scopes. Overall, an agent can usually tell tools apart, with a few legacy remnants.

Naming Consistency5/5

Tool names follow a consistent snake_case verb_noun pattern (browse_catalog, business_start, charge_create, etc.). Even the deprecated tools adhere to the same style. There are no mixed conventions or vague verbs like 'process' or 'run'. The naming is highly predictable.

Tool Count3/5

At 52 tools, this is a large surface. The domain is broad (marketplace buying/selling, business management, policy, storefront, distribution, authentication), so many tools are justifiable. However, four deprecated tools could be pruned, and the count is on the heavy side compared to typical MCP servers. It feels overengineered, yet each tool addresses a distinct facet of the platform.

Completeness4/5

The toolset covers the full lifecycle: discovery, evaluation, purchase, delivery, feedback, business management, policy, storefront, and distribution. Gaps are minor—for example, no direct way to list all services with full details without service_list, but that exists. The deprecated tools indicate ongoing migration to a consolidated search surface, suggesting good coverage. A few small gaps remain (e.g., no explicit 'update listing' for buyers, but that may not be needed).

Resources

Need Help?