Ranks the best AI tool or API per task: transcription, TTS, web search, scraping and OCR.
Given a natural-language question about which AI tool or API is best for a task (currently transcription, text-to-speech, web search, scraping & browser and ocr & document extraction), return Syftly's ranked recommendation: a citeable summary, a provider table with prices and trade-offs, dated sources, and a confidence label. Ask in plain English about price, accuracy, language or capability trade-offs — e.g. 'best OCR API for scanned PDFs' or 'best web scraping API for JavaScript-heavy sites'. Optionally pass "category" to disambiguate; otherwise it is detected from the question.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The question in natural language, e.g. 'best transcription API for Dutch'. | |
| category | No | Optional category id to disambiguate the question; omit to let Syftly detect it. |
| Name | Required | Description |
|---|---|---|
| slug | Yes | |
| query | Yes | The human question (page H1). |
| routing | Yes | Honest routing outcome: 'matched' = answered from a real category; 'none' = no category matched (out-of-scope/gibberish) — an honest no-match, not a fabricated answer; 'ambiguous' = fit 2+ categories. 'none'/'ambiguous' carry `categories` and no real recommendation/providers. |
| sources | Yes | |
| summary | Yes | Citeable summary, 40-80 words, reused verbatim across all views. On a no-match, the plain-language message. |
| updated | Yes | ISO date. |
| category | Yes | e.g. 'transcription'; '' on a no-match. |
| providers | Yes | |
| categories | No | Present only when routing !== 'matched': the supported categories so the caller can re-ask in scope. |
| confidence | Yes | Confidence/depth label. |
| recommendation | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so well: it explains that the tool returns a ranked recommendation, citeable summary, provider table with prices/trade-offs, dated sources, and a confidence label. It also discloses that category detection is automatic unless the optional category parameter is passed. It stops short of describing edge-case behavior (e.g., unsupported categories or unknown questions), but the core runtime behavior is transparent.
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?
The description is a single compact paragraph with three purposeful sentences: what it does and returns, how to phrase queries with examples, and how the optional category parameter behaves. Every sentence earns its place, and the most important information is 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?
Given that an output schema exists, the description does not need to explain return values in detail, but it still names the key output components. It also covers the input style, supported categories, and category-detection behavior. It could add caveats about unsupported domains or failure modes, but overall it is sufficiently complete for a tool of this complexity.
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?
The input schema already covers both parameters with 100% coverage, giving the baseline of 3. The description adds meaningful context beyond the schema: it clarifies that the query should be in plain English and can mention price, accuracy, language, or capability trade-offs, and it explains the purpose of the optional category parameter as a disambiguator with automatic detection when omitted.
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?
The description clearly states a specific purpose: given a natural-language question about choosing an AI tool/API, it returns a ranked recommendation with a cited summary, provider table, dated sources, and confidence label. It also enumerates the supported categories and gives concrete examples, making the tool's function unambiguous even without siblings.
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?
The description explicitly tells the user when to use the tool ('Given a natural-language question about which AI tool or API is best...') and instructs them to ask in plain English about trade-offs like price, accuracy, language, or capability. It does not state when not to use it or mention alternatives, but with no sibling tools provided, this is a minor gap.
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. Dates show when Glama detected each change.
find_best_tool31 fields changedOutput schema / properties / bronnenRemoved value: -{
- "items": {
- "properties": {
- "datum": {
- "description": "ISO date.",
- "type": "string"
- },
- "titel": {
- "type": "string"
- },
- "url": {
- "format": "uri",
- "type": "string"
- }
- },
- "required": [
- "titel",
- "url",
- "datum"
- ],
- "type": "object"
- },
- "type": "array"
-}Output schema / properties / categoriesAdded value: +{
+ "description": "Present only when routing !== 'matched': the supported categories so the caller can re-ask in scope.",
+ "items": {
+ "properties": {
+ "category": {
+ "description": "Supported category id, e.g. 'web-search'.",
+ "type": "string"
+ },
+ "label": {
+ "description": "Human label, e.g. 'Web search'.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "category",
+ "label"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+}Output schema / properties / category / descriptionPrevious value: -"e.g. 'transcription'."New value: +"e.g. 'transcription'; '' on a no-match."Output schema / properties / confidenceAdded value: +{
+ "description": "Confidence/depth label.",
+ "enum": [
+ "light estimate",
+ "hard tested"
+ ],
+ "type": "string"
+}Output schema / properties / hapRemoved value: -{
- "description": "Citeerbare kern, 40-80 words, reused verbatim across all views (ADR 0002).",
- "type": "string"
-}Output schema / properties / laatst_bijgewerktRemoved value: -{
- "description": "ISO date.",
- "type": "string"
-}Output schema / properties / providers / items / properties / bronRemoved value: -{
- "description": "Herkomst of this row's facts (ADR 0007/0008).",
- "type": "string"
-}Output schema / properties / providers / items / properties / bron_datumRemoved value: -{
- "description": "ISO date of the source.",
- "type": "string"
-}Output schema / properties / providers / items / properties / metrics / descriptionPrevious value: -"Open category-specific decision-axis fields (ADR 0010). Values are number, boolean, string or null (null = an honest gap, no Tier-1 source). Number metrics back min/max axes; boolean metrics back filter axes."New value: +"Open category-specific decision-axis fields. Keys are stable data identifiers (e.g. 'wer', 'latency_ms'); values are number, boolean, string or null (null = an honest gap). Number metrics back min/max axes; boolean metrics back filter axes."Output schema / properties / providers / items / properties / modelFamilieRemoved value: -{
- "description": "Filter-as, not a row of its own (ADR 0006).",
- "type": "string"
-}Output schema / properties / providers / items / properties / model_familyAdded value: +{
+ "description": "Filter attribute, not a row of its own.",
+ "type": "string"
+}Output schema / properties / providers / items / properties / naamRemoved value: -{
- "description": "The callable offering, e.g. 'Deepgram Nova-3'.",
- "type": "string"
-}Output schema / properties / providers / items / properties / nameAdded value: +{
+ "description": "The callable offering, e.g. 'Deepgram Nova-3'.",
+ "type": "string"
+}Output schema / properties / providers / items / properties / priceAdded value: +{
+ "properties": {
+ "comparable": {
+ "description": "false = token-/credit-priced, not directly comparable (excluded from the price axis).",
+ "type": "boolean"
+ },
+ "unit": {
+ "description": "e.g. '$/min', '$/1000min'.",
+ "type": "string"
+ },
+ "value": {
+ "type": [
+ "number",
+ "null"
+ ]
+ }
+ },
+ "required": [
+ "value",
+ "unit"
+ ],
+ "type": "object"
+}Output schema / properties / providers / items / properties / prijsRemoved value: -{
- "properties": {
- "eenheid": {
- "description": "e.g. '$/min', '$/1000min'.",
- "type": "string"
- },
- "vergelijkbaar": {
- "description": "false = token-/credit-priced, not directly comparable (ADR 0009).",
- "type": "boolean"
- },
- "waarde": {
- "type": [
- "number",
- "null"
- ]
- }
- },
- "required": [
- "waarde",
- "eenheid"
- ],
- "type": "object"
-}Output schema / properties / providers / items / properties / sourceAdded value: +{
+ "description": "Where this row's facts come from.",
+ "type": "string"
+}Output schema / properties / providers / items / properties / source_dateAdded value: +{
+ "description": "ISO date of the source.",
+ "type": "string"
+}Output schema / properties / providers / items / properties / sterkRemoved value: -{
- "type": "string"
-}Output schema / properties / providers / items / properties / strengthsAdded value: +{
+ "type": "string"
+}Output schema / properties / providers / items / properties / weaknessesAdded value: +{
+ "type": "string"
+}Output schema / properties / providers / items / properties / zwakRemoved value: -{
- "type": "string"
-}Output schema / properties / providers / items / requiredPrevious value: -[
- "naam",
- "provider",
- "prijs",
- "metrics",
- "sterk",
- "zwak",
- "bron",
- "bron_datum"
-]New value: +[
+ "name",
+ "provider",
+ "price",
+ "metrics",
+ "strengths",
+ "weaknesses",
+ "source",
+ "source_date"
+]Output schema / properties / recommendation / properties / axes / descriptionPrevious value: -"Decision-as -> recommended aanbod."New value: +"Decision-axis -> recommended offering. Carries EVERY matched axis: filters + all ordering axes, each naming its own computed winner."Output schema / properties / recommendation / properties / default / descriptionPrevious value: -"Naam of the recommended Provider-aanbod."New value: +"Name of the recommended offering ('' on a no-match)."Output schema / properties / recommendation / properties / primaryAdded value: +{
+ "description": "The axis key whose winner became `default` when 2+ ordering axes conflict with no composite tiebreak — the earliest-in-query axis. Absent for single-axis/composite-resolved answers.",
+ "type": "string"
+}Output schema / properties / routingAdded value: +{
+ "description": "Honest routing outcome: 'matched' = answered from a real category; 'none' = no category matched (out-of-scope/gibberish) — an honest no-match, not a fabricated answer; 'ambiguous' = fit 2+ categories. 'none'/'ambiguous' carry `categories` and no real recommendation/providers.",
+ "enum": [
+ "matched",
+ "none",
+ "ambiguous"
+ ],
+ "type": "string"
+}Output schema / properties / sourcesAdded value: +{
+ "items": {
+ "properties": {
+ "date": {
+ "description": "ISO date.",
+ "type": "string"
+ },
+ "title": {
+ "type": "string"
+ },
+ "url": {
+ "format": "uri",
+ "type": "string"
+ }
+ },
+ "required": [
+ "title",
+ "url",
+ "date"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+}Output schema / properties / summaryAdded value: +{
+ "description": "Citeable summary, 40-80 words, reused verbatim across all views. On a no-match, the plain-language message.",
+ "type": "string"
+}Output schema / properties / updatedAdded value: +{
+ "description": "ISO date.",
+ "type": "string"
+}Output schema / properties / zekerheidslabelRemoved value: -{
- "description": "Confidence/depth label (ADR 0001).",
- "enum": [
- "light estimate",
- "hard tested"
- ],
- "type": "string"
-}Output schema / requiredPrevious value: -[
- "query",
- "slug",
- "category",
- "hap",
- "zekerheidslabel",
- "laatst_bijgewerkt",
- "recommendation",
- "providers",
- "bronnen"
-]New value: +[
+ "query",
+ "slug",
+ "category",
+ "routing",
+ "summary",
+ "confidence",
+ "updated",
+ "recommendation",
+ "providers",
+ "sources"
+]find_best_toolClaiming proves that you control a remote MCP connector. It does not move, proxy, or interrupt the server.
Open the connector listing, choose Claim ownership, and sign in to Glama.
Complete one verification method:
GitHub identity — fastest for official registry listings. For a namespace such as io.github.alice/server, link the matching GitHub user, then choose Claim with GitHub. An organization namespace such as io.github.acme/server also needs that organization to have installed the Glama AI GitHub App and approved its permissions, because GitHub discloses organization membership only to apps it has installed. Use HTTP or DNS when it has not.
HTTP challenge — works when you can deploy a public file. Generate a token, publish the exact JSON Glama shows at /.well-known/glama.json on the same origin as the connector, then choose Check HTTP challenge.
DNS challenge — works when you control DNS but cannot change the server. Generate a token, create the exact TXT record Glama shows, wait for it to propagate, then choose Check DNS challenge.
After verification, Glama sends a confirmation email and gives you access to listing details, thumbnails, health checks, and analytics. Keep the HTTP file or DNS record in place: Glama periodically checks it and ownership remains verified while the token is discoverable.
The HTTP ownership file has this structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"claim": "glama_claim_..."
}Claim tokens are opaque, stable, and bound to the signed-in Glama account. They contain no email address or other personal information. If Glama can no longer discover a verified HTTP or DNS token, it starts a seven-day grace period before removing claim-based access. Restore the same token during that period to keep ownership verified. Never publish an email address, Glama session token, GitHub token, or connector credential as ownership proof.
If verification fails, confirm that you copied the current token exactly. The HTTP file must be public, return valid JSON with a successful HTTP response, and stay on the connector's origin. DNS changes may need more time to propagate. A claim cannot transfer to a different origin or hostname: if the connector target changes, Glama starts the grace period and the new target must be claimed separately after the previous claim is released.
For a connector linked to the official MCP Registry, registry updates continue to replace its name, description, and URL by default. After claiming, open Manage connector and enable Use Glama listing details as the source of truth if edits made on Glama should be preserved. Categories and thumbnails are always managed on Glama; registry linkage and technical connection settings continue to sync.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
To improve your MCP server's ranking:
Claim ownership of the server listing
Complete the server profile with an accurate description and thumbnail
Provide a test profile so Glama can connect to and evaluate the server
Keep tool definitions clear and complete to earn a high Tool Definition Quality Score (TDQS)
Route real usage through the Glama Gateway; more recorded successful server uses also improve the ranking
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
No comments yet. Be the first to start the discussion!
35 AI tools for image/video generation, TTS, transcription, OCR & embeddings via deAPI
15 media & data tools for AI agents: search, transcribe, subtitles, voiceover, translate & more.
Consensus 'best X for Y' rankings from ChatGPT, Claude, Gemini & Grok. Search, verdicts, history.
The best web search for your AI Agent
Add one secure layer between your agents and this server.
With only one tool, there is no possibility of confusion between tools. The tool's purpose is clearly defined and unique.
The single tool uses a clear snake_case verb_noun pattern ('find_best_tool'), which is predictable and readable even though there is only one tool.
One tool is on the borderline of feeling thin, but it serves a single, well-defined purpose. Still, a server with one tool feels minimal and could benefit from additional related tools.
The tool completely covers its stated scope, handling multiple categories (transcription, TTS, web search, scraping, OCR) with optional category disambiguation. There are no obvious missing operations within its intended purpose.
