Poly-Glot AI Workspace
Server Details
Multilingual AI workspace: 1,000+ prompts, Compare Mode, 35 languages, BYOM. Free trial.
- Status
- Healthy
- Uptime
- 95.6% over 35 days
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- hmoses/poly-glot-ai-workspace
- GitHub Stars
- 0
- Server Listing
- polyglot-mcp
TDQS
Scored across 15 tools
Most tools have distinct purposes (translation vs localization vs language detection are clearly separated), but translate_text and localize_text could be confused by an agent since both handle text transformation into another language. The descriptions help differentiate them, but the boundary is subtle.
The tool names mostly follow a verb_noun pattern (detect_language, get_template, search_templates, translate_text, transcribe_audio). Minor deviations exist: build_prompt, open_workspace, and prepare_compare are less predictable but still readable and consistent in style.
15 tools is at the upper edge of the well-scoped range but each tool serves a distinct function in the Poly-Glot ecosystem (templates, subscription, language ops, custom models, compare mode). A few tools like get_custom_model_capabilities and validate_custom_model could potentially be merged, but the count is reasonable for the breadth.
The surface covers the core workflows: language detection/translation/localization, template browsing/searching/building, subscription management, and custom model validation/execution. Minor gaps exist: there's no tool to update or delete templates, and no way to manage saved custom models beyond validation, but agents can work around these.
Available Tools
15 toolsbuild_promptBuild a Poly-Glot promptInspect
Fill a named Poly-Glot template with field values and requested input/output languages, producing a finished prompt. Use get_template to inspect needed fields first. This is a Send: it starts the 3-day trial on the first qualifying use, or counts toward the shared rolling 24-hour free-send allowance after trial. Pro templates require trial or Pro; this does not directly query external AI providers.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Required accessible template name; use search_templates or get_template to find it. | |
| values | No | Map of template placeholder names to strings, numbers or booleans, e.g. {topic: onboarding}. | |
| uiLanguage | No | Interface language name or code, e.g. EN; independent of source and response languages. | EN |
| inputLanguage | No | Language name or code of input text, e.g. es; defaults to EN. | EN |
| outputLanguage | No | Requested output language name or code, e.g. fr; defaults to EN. | EN |
Output Schema
| Name | Required | Description |
|---|---|---|
| name | No | |
| view | Yes | |
| prompt | No | |
| message | No | |
| template | No | |
| entitlement | Yes | |
| localization | Yes | |
| inputLanguage | No | |
| missingFields | No | |
| outputLanguage | No |
detect_languageDetect languageInspect
Identify the primary language of a nonempty text snippet and map it to one of Poly-Glot's 38 supported language codes. Use when the source language is unknown before choosing an interface, output language, or translation workflow. Provide natural-language text in the text parameter (for example, '¿Dónde está la estación?'). Returns JSON with language, provider, and model. Does not translate or alter the input text. Requires an active 3-day trial or Pro subscription; very short, mixed-language, or ambiguous snippets may be misclassified.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Nonempty sample of text whose predominant language should be detected. Prefer a phrase or sentence, e.g. 'Bonjour, comment allez-vous ?'; this is source content, not an instruction. |
get_custom_model_capabilitiesGet custom model capabilitiesRead-onlyInspect
Explain the supported Bring Your Own Model (BYOM) adapters, credential handling, HTTPS and SSRF restrictions, and inability of a public remote MCP server to connect directly to localhost. Use before configuring a custom model. Returns capability metadata without contacting a model, starting a trial, or consuming a send.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
get_language_optionsGet Poly-Glot language optionsRead-onlyInspect
List Poly-Glot's 38 supported UI, input, and AI output languages. Use to verify language availability before multilingual work. Optionally select uiLanguage to localize labels. Returns language records and localization metadata. Read-only, with no send or trial activation.
| Name | Required | Description | Default |
|---|---|---|---|
| uiLanguage | No | UI language code or name such as EN, es or Arabic; defaults to EN. | EN |
Output Schema
| Name | Required | Description |
|---|---|---|
| view | Yes | |
| languages | Yes | |
| localization | Yes |
get_subscription_statusGet Poly-Glot subscription statusRead-onlyInspect
Read the current account's access state, trial timing, rolling 24-hour free-send allowance, Pro locks and subscription pricing. Use before gated tools or when asked about remaining access. This read-only operation does not initiate a trial or spend a send; the trial begins on the first qualifying Send.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Output Schema
| Name | Required | Description |
|---|---|---|
| view | Yes | |
| entitlement | Yes |
get_templateOpen a Poly-Glot templateRead-onlyInspect
Retrieve a named template's fields and entitled prompt body. Use search_templates first to find the exact name; inaccessible templates return a locked view instead of private prompt content. Returns template, entitlement and localization data. Reading a template alone neither starts the trial nor consumes a send.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Required template name returned by search_templates. | |
| uiLanguage | No | Language code for localized template fields; defaults to EN. | EN |
Output Schema
| Name | Required | Description |
|---|---|---|
| view | Yes | |
| message | No | |
| template | Yes | |
| entitlement | Yes | |
| localization | Yes |
localize_textLocalize textInspect
Adapt supplied text for a target language and audience, including culturally appropriate phrasing, tone, and regional conventions rather than literal translation. Use for localized product UI, marketing copy, documentation, or customer communications; use translate_text for a closer translation. Set required targetLanguage and optionally locale (e.g. 'es-MX'), audience, and tone. Returns JSON containing localized text, targetLanguage, locale, provider, and model. Requires an active trial or Pro. Review sensitive, legal, and technical output with a qualified local reviewer.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Original nonempty copy to adapt for the target culture, region, and audience. | |
| tone | No | Desired writing style, such as 'friendly', 'formal', or 'concise'. | |
| locale | No | Optional regional locale, such as 'es-MX', 'fr-CA', or 'en-GB'; affects regional spelling and conventions. | |
| audience | No | Intended readers or customers, e.g. 'first-time mobile app users' or 'enterprise developers'. | |
| targetLanguage | Yes | Required output language name or code, e.g. 'Arabic' or 'ar'. |
open_workspaceOpen Poly-Glot AI WorkspaceRead-onlyInspect
Open the embedded Poly-Glot prompt workspace and template browser, optionally prefiltered by a query and translated via uiLanguage. Returns searchable template records, their locked states, entitlement and localization. Browsing is read-only and does not start the trial or use a send.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Optional keyword or goal for template search, e.g. resume. Maximum 200 characters. | |
| uiLanguage | No | UI language name or code for template labels; defaults to EN. | EN |
Output Schema
| Name | Required | Description |
|---|---|---|
| view | Yes | |
| query | Yes | |
| results | Yes | |
| entitlement | Yes | |
| localization | Yes |
prepare_comparePrepare Poly-Glot Compare ModeInspect
Prepare the same canonical prompt for two to nine selected AI providers using a raw prompt or accessible template. Returns provider destinations, prompt and usage instructions without calling third-party models. This is a Send and begins the 3-day trial on first qualifying use; Compare Mode requires active trial or Pro. Use when a user explicitly wants side-by-side answers.
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | Optional accessible template name; supply this or a raw prompt. | |
| prompt | No | Optional original prompt for each provider, maximum 30,000 characters; provide this or name. | |
| values | No | Placeholder values used when preparing a named template. | |
| providers | No | Two to nine provider IDs; defaults to ChatGPT and Claude and duplicates are removed. | |
| uiLanguage | No | Interface language name or code, e.g. EN; independent of source and response languages. | EN |
| inputLanguage | No | Language name or code of input text, e.g. es; defaults to EN. | EN |
| outputLanguage | No | Requested output language name or code, e.g. fr; defaults to EN. | EN |
Output Schema
| Name | Required | Description |
|---|---|---|
| view | Yes | |
| prompt | No | |
| message | No | |
| template | No | |
| providers | No | |
| entitlement | Yes | |
| instructions | No | |
| localization | Yes | |
| sourceTemplate | No |
prepare_custom_comparePrepare custom Compare ModeInspect
Prepare a canonical prompt and instructions for comparing at least two targets, including one to five custom BYOM models and optional supported built-in AI providers. API keys must not appear in the comparison plan; use run_custom_model to execute custom targets separately. Returns comparison targets and prompt without invoking any models. This is a Send and starts the 3-day trial on first qualifying use; Compare Mode requires trial or Pro.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | Required canonical prompt shared among all selected models, up to 30,000 characters. | |
| uiLanguage | No | Interface language name or code, e.g. EN; independent of source and response languages. | EN |
| customModels | Yes | Required array of 1 to 5 custom model connection descriptors; excludes authentication credentials. | |
| inputLanguage | No | Language name or code of input text, e.g. es; defaults to EN. | EN |
| outputLanguage | No | Requested output language name or code, e.g. fr; defaults to EN. | EN |
| builtinProviders | No | Optional built-in provider IDs to include alongside custom targets. This preparation tool does not call providers. |
run_custom_modelRun a custom modelInspect
Run a user-supplied prompt against a developer-provided OpenAI-compatible or custom REST HTTPS model endpoint. Use validate_custom_model to test URL and adapter settings before sending. Returns model-generated text, model name, optional usage, and account state. Requires active trial or Pro and transmits prompt content to the selected provider. Credentials are transient, not persisted; localhost/private networks are not supported.
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | Model identifier at the custom provider, when needed. | |
| apiKey | No | Transient authentication key sent to the chosen provider; never log or embed in prompts. | |
| prompt | Yes | Required nonempty prompt to send externally, maximum 30,000 characters. | |
| system | No | Optional system instructions supported by the endpoint. | |
| baseUrl | No | Required public HTTPS base URL for openai-compatible mode. | |
| authMode | No | Custom REST authentication mode, default bearer. | bearer |
| endpoint | No | Required public HTTPS inference URL for custom-rest mode. | |
| maxTokens | No | Optional maximum output token count, subject to model limits. | |
| uiLanguage | No | Interface language name or code, e.g. EN; independent of source and response languages. | EN |
| adapterMode | Yes | Adapter for the target endpoint: openai-compatible or custom-rest. | |
| promptField | No | Custom REST request JSON key for prompt content. | prompt |
| systemField | No | Custom REST request JSON key for system instructions. | system |
| temperature | No | Optional response sampling randomness between 0 and 2. | |
| apiKeyHeader | No | Custom REST API-key authentication header name. | x-api-key |
| extraHeaders | No | Extra HTTP headers required by the provider, if any. | |
| inputLanguage | No | Language name or code of input text, e.g. es; defaults to EN. | EN |
| outputLanguage | No | Requested output language name or code, e.g. fr; defaults to EN. | EN |
| responseTextPath | No | Optional JSON response field/path containing generated text. |
search_templatesSearch Poly-Glot templatesRead-onlyInspect
Search Poly-Glot's template catalog by keywords and goal, optionally filtered to free or Pro results. Use before get_template or build_prompt when the exact name is unknown. Results contain template metadata, tier and entitlement status. Searching is read-only and does not trigger a send or trial.
| Name | Required | Description | Default |
|---|---|---|---|
| goal | No | Optional intended outcome, e.g. write a help article. | |
| plan | No | Filter catalog by free or Pro tier; filtering does not grant access. | |
| limit | No | Maximum matches to return (1 to 24), default 12. | |
| query | No | Search phrase or topic; blank lists available templates. | |
| uiLanguage | No | Language code for localized template labels; defaults to EN. | EN |
Output Schema
| Name | Required | Description |
|---|---|---|
| view | Yes | |
| query | Yes | |
| results | Yes | |
| entitlement | Yes | |
| localization | Yes |
transcribe_audioTranscribe audioInspect
Convert audio to transcript text for Poly-Glot workflows. Use for supplied speech recordings, not for translating text. Provide exactly one source: a publicly reachable HTTPS audioUrl or base64-encoded audioBase64 (without a data-URL prefix). For base64 audio, supply mimeType and filename when known; languageHint can improve recognition. Set detectLanguage=true to identify the resulting text's language. Requires an active trial or Pro. Returns JSON containing transcript text, optional detectedLanguage, provider, and model. Audio is submitted to a transcription provider; do not send material without permission.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | No | Optional recognition context, such as expected names or specialist vocabulary; not the text to transcribe. | |
| audioUrl | No | Public HTTPS URL of an audio recording to transcribe. Use this OR audioBase64, never both; private or local URLs are not supported. | |
| filename | No | Original audio filename with extension, such as meeting.m4a, to help determine the format. | |
| mimeType | No | Audio MIME type, such as audio/mpeg, audio/mp4, or audio/wav. Recommended for base64 input. | |
| audioBase64 | No | Base64-encoded audio bytes, without a data: prefix. Alternative to audioUrl; provide exactly one audio source. | |
| languageHint | No | Optional language hint for speech recognition, such as en, es, or fr. Leave blank if unknown. | |
| detectLanguage | No | When true, also infer a supported Poly-Glot language from the resulting transcript; defaults to false. |
translate_textTranslate textInspect
Translate supplied text into one of Poly-Glot's 38 supported languages while aiming to preserve meaning, names, formatting, code, and URLs. Use for translation rather than cultural adaptation; use localize_text when audience, tone, or regional conventions must change. Specify required targetLanguage (language name or code, e.g. 'es'); set sourceLanguage to 'auto' to detect the source automatically. Returns JSON containing translated text, targetLanguage, provider, and model; quality can vary with idiom and context. Requires an active trial or Pro; text is processed by the configured translation provider.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Nonempty original text to translate, including any formatting to preserve. | |
| sourceLanguage | No | Original language name or code, such as 'en' or 'English'; 'auto' (default) asks the provider to detect it. | auto |
| targetLanguage | Yes | Required desired output language name or code among the 38 supported, e.g. 'Spanish' or 'es'. |
validate_custom_modelValidate a custom model endpointRead-onlyInspect
Validate the HTTPS URL and adapter configuration for an external custom model. For OpenAI-compatible mode provide baseUrl; for custom REST use endpoint. Set probe=true only when an actual minimal request to the external provider is intended. Returns validation or probe status; credentials are transient and never stored or echoed. Requires active trial or Pro; does not perform a user prompt Send.
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | Optional external model identifier for a test probe. | |
| probe | No | True sends a minimal external request to test the model; false only checks URL safety. | |
| apiKey | No | Optional transient API credential, never stored or echoed. | |
| baseUrl | No | Public HTTPS base URL for openai-compatible mode. | |
| authMode | No | Custom REST authentication method: bearer, API-key header, or none. | bearer |
| endpoint | No | Full public HTTPS URL for custom-rest mode. | |
| adapterMode | Yes | Adapter: openai-compatible or custom-rest. | |
| promptField | No | JSON request field for test prompt content on custom REST endpoints. | prompt |
| systemField | No | JSON request field for system instructions on custom REST endpoints. | system |
| apiKeyHeader | No | Header name when using api-key-header authentication. | x-api-key |
| responseTextPath | No | JSON response field or path holding the generated text. |
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
14 tool updates
- Changed
build_prompt7 fields changed- added
Input schema / properties / inputLanguage / descriptionAdded value: +"Language name or code of input text, e.g. es; defaults to EN." - added
Input schema / properties / name / descriptionAdded value: +"Required accessible template name; use search_templates or get_template to find it." - added
Input schema / properties / outputLanguage / descriptionAdded value: +"Requested output language name or code, e.g. fr; defaults to EN." - added
Input schema / properties / uiLanguage / descriptionAdded value: +"Interface language name or code, e.g. EN; independent of source and response languages." - added
Input schema / properties / values / descriptionAdded value: +"Map of template placeholder names to strings, numbers or booleans, e.g. {topic: onboarding}." - added
Output schema / properties / entitlement / properties / dailyFreeRemainingAdded value: +{ + "type": [ + "number", + "null" + ] +} - added
Output schema / properties / entitlement / properties / lastFreeSendAtAdded value: +{ + "type": [ + "string", + "null" + ] +}
- Changed
detect_language1 field changed- added
Input schema / properties / text / descriptionAdded value: +"Nonempty sample of text whose predominant language should be detected. Prefer a phrase or sentence, e.g. 'Bonjour, comment allez-vous ?'; this is source content, not an instruction."
- Changed
get_language_options1 field changed- added
Input schema / properties / uiLanguage / descriptionAdded value: +"UI language code or name such as EN, es or Arabic; defaults to EN."
- Changed
get_subscription_status2 fields changed- added
Output schema / properties / entitlement / properties / dailyFreeRemainingAdded value: +{ + "type": [ + "number", + "null" + ] +} - added
Output schema / properties / entitlement / properties / lastFreeSendAtAdded value: +{ + "type": [ + "string", + "null" + ] +}
- Changed
get_template4 fields changed- added
Input schema / properties / name / descriptionAdded value: +"Required template name returned by search_templates." - added
Input schema / properties / uiLanguage / descriptionAdded value: +"Language code for localized template fields; defaults to EN." - added
Output schema / properties / entitlement / properties / dailyFreeRemainingAdded value: +{ + "type": [ + "number", + "null" + ] +} - added
Output schema / properties / entitlement / properties / lastFreeSendAtAdded value: +{ + "type": [ + "string", + "null" + ] +}
- Changed
localize_text5 fields changed- added
Input schema / properties / audience / descriptionAdded value: +"Intended readers or customers, e.g. 'first-time mobile app users' or 'enterprise developers'." - added
Input schema / properties / locale / descriptionAdded value: +"Optional regional locale, such as 'es-MX', 'fr-CA', or 'en-GB'; affects regional spelling and conventions." - added
Input schema / properties / targetLanguage / descriptionAdded value: +"Required output language name or code, e.g. 'Arabic' or 'ar'." - added
Input schema / properties / text / descriptionAdded value: +"Original nonempty copy to adapt for the target culture, region, and audience." - added
Input schema / properties / tone / descriptionAdded value: +"Desired writing style, such as 'friendly', 'formal', or 'concise'."
- Changed
open_workspace4 fields changed- added
Input schema / properties / query / descriptionAdded value: +"Optional keyword or goal for template search, e.g. resume. Maximum 200 characters." - added
Input schema / properties / uiLanguage / descriptionAdded value: +"UI language name or code for template labels; defaults to EN." - added
Output schema / properties / entitlement / properties / dailyFreeRemainingAdded value: +{ + "type": [ + "number", + "null" + ] +} - added
Output schema / properties / entitlement / properties / lastFreeSendAtAdded value: +{ + "type": [ + "string", + "null" + ] +}
- Changed
prepare_compare11 fields changed- added
Input schema / properties / inputLanguage / descriptionAdded value: +"Language name or code of input text, e.g. es; defaults to EN." - added
Input schema / properties / name / descriptionAdded value: +"Optional accessible template name; supply this or a raw prompt." - added
Input schema / properties / outputLanguage / descriptionAdded value: +"Requested output language name or code, e.g. fr; defaults to EN." - added
Input schema / properties / prompt / descriptionAdded value: +"Optional original prompt for each provider, maximum 30,000 characters; provide this or name." - added
Input schema / properties / providers / descriptionAdded value: +"Two to nine provider IDs; defaults to ChatGPT and Claude and duplicates are removed." - changed
Input schema / properties / providers / items / enumPrevious value: -[ - "chatgpt", - "claude", - "gemini", - "perplexity", - "grok", - "copilot", - "mistral" -]New value: +[ + "chatgpt", + "claude", + "gemini", + "perplexity", + "grok", + "copilot", + "mistral", + "huggingchat", + "duckduckgo" +] - changed
Input schema / properties / providers / maxItemsPrevious value: -7New value: +9 - added
Input schema / properties / uiLanguage / descriptionAdded value: +"Interface language name or code, e.g. EN; independent of source and response languages." - added
Input schema / properties / values / descriptionAdded value: +"Placeholder values used when preparing a named template." - added
Output schema / properties / entitlement / properties / dailyFreeRemainingAdded value: +{ + "type": [ + "number", + "null" + ] +} - added
Output schema / properties / entitlement / properties / lastFreeSendAtAdded value: +{ + "type": [ + "string", + "null" + ] +}
- Changed
prepare_custom_compare12 fields changed- added
Input schema / properties / builtinProviders / descriptionAdded value: +"Optional built-in provider IDs to include alongside custom targets. This preparation tool does not call providers." - changed
Input schema / properties / builtinProviders / items / enumPrevious value: -[ - "chatgpt", - "claude", - "gemini", - "perplexity", - "grok", - "copilot", - "mistral" -]New value: +[ + "chatgpt", + "claude", + "gemini", + "perplexity", + "grok", + "copilot", + "mistral", + "huggingchat", + "duckduckgo" +] - added
Input schema / properties / customModels / descriptionAdded value: +"Required array of 1 to 5 custom model connection descriptors; excludes authentication credentials." - added
Input schema / properties / customModels / items / properties / adapterMode / descriptionAdded value: +"Adapter type for this model's API." - added
Input schema / properties / customModels / items / properties / baseUrl / descriptionAdded value: +"Public HTTPS base URL for an OpenAI-compatible model." - added
Input schema / properties / customModels / items / properties / endpoint / descriptionAdded value: +"Public HTTPS inference URL for a custom REST model." - added
Input schema / properties / customModels / items / properties / label / descriptionAdded value: +"Human-readable name of the custom model in the comparison results." - added
Input schema / properties / customModels / items / properties / model / descriptionAdded value: +"Optional external model identifier." - added
Input schema / properties / inputLanguage / descriptionAdded value: +"Language name or code of input text, e.g. es; defaults to EN." - added
Input schema / properties / outputLanguage / descriptionAdded value: +"Requested output language name or code, e.g. fr; defaults to EN." - added
Input schema / properties / prompt / descriptionAdded value: +"Required canonical prompt shared among all selected models, up to 30,000 characters." - added
Input schema / properties / uiLanguage / descriptionAdded value: +"Interface language name or code, e.g. EN; independent of source and response languages."
- Changed
run_custom_model18 fields changed- added
Input schema / properties / adapterMode / descriptionAdded value: +"Adapter for the target endpoint: openai-compatible or custom-rest." - added
Input schema / properties / apiKey / descriptionAdded value: +"Transient authentication key sent to the chosen provider; never log or embed in prompts." - added
Input schema / properties / apiKeyHeader / descriptionAdded value: +"Custom REST API-key authentication header name." - added
Input schema / properties / authMode / descriptionAdded value: +"Custom REST authentication mode, default bearer." - added
Input schema / properties / baseUrl / descriptionAdded value: +"Required public HTTPS base URL for openai-compatible mode." - added
Input schema / properties / endpoint / descriptionAdded value: +"Required public HTTPS inference URL for custom-rest mode." - added
Input schema / properties / extraHeaders / descriptionAdded value: +"Extra HTTP headers required by the provider, if any." - added
Input schema / properties / inputLanguage / descriptionAdded value: +"Language name or code of input text, e.g. es; defaults to EN." - added
Input schema / properties / maxTokens / descriptionAdded value: +"Optional maximum output token count, subject to model limits." - added
Input schema / properties / model / descriptionAdded value: +"Model identifier at the custom provider, when needed." - added
Input schema / properties / outputLanguage / descriptionAdded value: +"Requested output language name or code, e.g. fr; defaults to EN." - added
Input schema / properties / prompt / descriptionAdded value: +"Required nonempty prompt to send externally, maximum 30,000 characters." - added
Input schema / properties / promptField / descriptionAdded value: +"Custom REST request JSON key for prompt content." - added
Input schema / properties / responseTextPath / descriptionAdded value: +"Optional JSON response field/path containing generated text." - added
Input schema / properties / system / descriptionAdded value: +"Optional system instructions supported by the endpoint." - added
Input schema / properties / systemField / descriptionAdded value: +"Custom REST request JSON key for system instructions." - added
Input schema / properties / temperature / descriptionAdded value: +"Optional response sampling randomness between 0 and 2." - added
Input schema / properties / uiLanguage / descriptionAdded value: +"Interface language name or code, e.g. EN; independent of source and response languages."
- Changed
search_templates7 fields changed- added
Input schema / properties / goal / descriptionAdded value: +"Optional intended outcome, e.g. write a help article." - added
Input schema / properties / limit / descriptionAdded value: +"Maximum matches to return (1 to 24), default 12." - added
Input schema / properties / plan / descriptionAdded value: +"Filter catalog by free or Pro tier; filtering does not grant access." - added
Input schema / properties / query / descriptionAdded value: +"Search phrase or topic; blank lists available templates." - added
Input schema / properties / uiLanguage / descriptionAdded value: +"Language code for localized template labels; defaults to EN." - added
Output schema / properties / entitlement / properties / dailyFreeRemainingAdded value: +{ + "type": [ + "number", + "null" + ] +} - added
Output schema / properties / entitlement / properties / lastFreeSendAtAdded value: +{ + "type": [ + "string", + "null" + ] +}
- Changed
transcribe_audio7 fields changed- added
Input schema / properties / audioBase64 / descriptionAdded value: +"Base64-encoded audio bytes, without a data: prefix. Alternative to audioUrl; provide exactly one audio source." - added
Input schema / properties / audioUrl / descriptionAdded value: +"Public HTTPS URL of an audio recording to transcribe. Use this OR audioBase64, never both; private or local URLs are not supported." - added
Input schema / properties / detectLanguage / descriptionAdded value: +"When true, also infer a supported Poly-Glot language from the resulting transcript; defaults to false." - added
Input schema / properties / filename / descriptionAdded value: +"Original audio filename with extension, such as meeting.m4a, to help determine the format." - added
Input schema / properties / languageHint / descriptionAdded value: +"Optional language hint for speech recognition, such as en, es, or fr. Leave blank if unknown." - added
Input schema / properties / mimeType / descriptionAdded value: +"Audio MIME type, such as audio/mpeg, audio/mp4, or audio/wav. Recommended for base64 input." - added
Input schema / properties / prompt / descriptionAdded value: +"Optional recognition context, such as expected names or specialist vocabulary; not the text to transcribe."
- Changed
translate_text3 fields changed- added
Input schema / properties / sourceLanguage / descriptionAdded value: +"Original language name or code, such as 'en' or 'English'; 'auto' (default) asks the provider to detect it." - added
Input schema / properties / targetLanguage / descriptionAdded value: +"Required desired output language name or code among the 38 supported, e.g. 'Spanish' or 'es'." - added
Input schema / properties / text / descriptionAdded value: +"Nonempty original text to translate, including any formatting to preserve."
- Changed
validate_custom_model11 fields changed- added
Input schema / properties / adapterMode / descriptionAdded value: +"Adapter: openai-compatible or custom-rest." - added
Input schema / properties / apiKey / descriptionAdded value: +"Optional transient API credential, never stored or echoed." - added
Input schema / properties / apiKeyHeader / descriptionAdded value: +"Header name when using api-key-header authentication." - added
Input schema / properties / authMode / descriptionAdded value: +"Custom REST authentication method: bearer, API-key header, or none." - added
Input schema / properties / baseUrl / descriptionAdded value: +"Public HTTPS base URL for openai-compatible mode." - added
Input schema / properties / endpoint / descriptionAdded value: +"Full public HTTPS URL for custom-rest mode." - added
Input schema / properties / model / descriptionAdded value: +"Optional external model identifier for a test probe." - added
Input schema / properties / probe / descriptionAdded value: +"True sends a minimal external request to test the model; false only checks URL safety." - added
Input schema / properties / promptField / descriptionAdded value: +"JSON request field for test prompt content on custom REST endpoints." - added
Input schema / properties / responseTextPath / descriptionAdded value: +"JSON response field or path holding the generated text." - added
Input schema / properties / systemField / descriptionAdded value: +"JSON request field for system instructions on custom REST endpoints."
6 tool updates
- Changed
build_prompt3 fields changed- added
Output schema / properties / entitlement / properties / compareLockedAdded value: +{ + "type": "boolean" +} - added
Output schema / properties / entitlement / properties / dailyFreeLimitAdded value: +{ + "type": [ + "number", + "null" + ] +} - added
Output schema / properties / entitlement / properties / nextResetAtAdded value: +{ + "type": [ + "string", + "null" + ] +}
- Changed
get_subscription_status3 fields changed- added
Output schema / properties / entitlement / properties / compareLockedAdded value: +{ + "type": "boolean" +} - added
Output schema / properties / entitlement / properties / dailyFreeLimitAdded value: +{ + "type": [ + "number", + "null" + ] +} - added
Output schema / properties / entitlement / properties / nextResetAtAdded value: +{ + "type": [ + "string", + "null" + ] +}
- Changed
get_template3 fields changed- added
Output schema / properties / entitlement / properties / compareLockedAdded value: +{ + "type": "boolean" +} - added
Output schema / properties / entitlement / properties / dailyFreeLimitAdded value: +{ + "type": [ + "number", + "null" + ] +} - added
Output schema / properties / entitlement / properties / nextResetAtAdded value: +{ + "type": [ + "string", + "null" + ] +}
- Changed
open_workspace3 fields changed- added
Output schema / properties / entitlement / properties / compareLockedAdded value: +{ + "type": "boolean" +} - added
Output schema / properties / entitlement / properties / dailyFreeLimitAdded value: +{ + "type": [ + "number", + "null" + ] +} - added
Output schema / properties / entitlement / properties / nextResetAtAdded value: +{ + "type": [ + "string", + "null" + ] +}
- Changed
prepare_compare3 fields changed- added
Output schema / properties / entitlement / properties / compareLockedAdded value: +{ + "type": "boolean" +} - added
Output schema / properties / entitlement / properties / dailyFreeLimitAdded value: +{ + "type": [ + "number", + "null" + ] +} - added
Output schema / properties / entitlement / properties / nextResetAtAdded value: +{ + "type": [ + "string", + "null" + ] +}
- Changed
search_templates3 fields changed- added
Output schema / properties / entitlement / properties / compareLockedAdded value: +{ + "type": "boolean" +} - added
Output schema / properties / entitlement / properties / dailyFreeLimitAdded value: +{ + "type": [ + "number", + "null" + ] +} - added
Output schema / properties / entitlement / properties / nextResetAtAdded value: +{ + "type": [ + "string", + "null" + ] +}
15 tool updates
- First observed
build_prompt - First observed
detect_language - First observed
get_custom_model_capabilities - First observed
get_language_options - First observed
get_subscription_status - First observed
get_template - First observed
localize_text - First observed
open_workspace - First observed
prepare_compare - First observed
prepare_custom_compare - First observed
run_custom_model - First observed
search_templates - First observed
transcribe_audio - First observed
translate_text - First observed
validate_custom_model
Related MCP Connectors
Test and compare prompts across any AI provider. Bring your own keys.
AI visibility across 8 LLM platforms. 30 tools, most need no API key. EU-hosted, free.
Free live chat and AI support agent. Auto-create a workspace and embed from your AI editor.
One key, 100+ models: chat with any LLM, generate images and speech. Live model list. Free trial.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceFree AI prompt orchestration with 185 expert roles, 1,741 templates, and 4 MCP tools — no API key requiredMIT
- AlicenseAqualityFmaintenanceAI content generation, repurposing, and multi-platform publishing for 9+ social media platforms. Generate blog posts, discover trending topics, brainstorm titles, and publish to Twitter, LinkedIn, Bluesky, and more.854 npm7MIT

Prompeteer MCP Serverofficial
AlicenseNot gradedqualityBmaintenanceGenerate and review AI prompts and reusable agent skills, work with saved PromptDrive prompts, and retrieve permitted Memory context. Connect at https://prompeteer.ai/mcp using Streamable HTTP and OAuth 2.1. Tool access depends on granted scopes; review generated output before use.44 npm1MIT- AlicenseNot gradedqualityBmaintenanceEnables comparing outputs of 17 large language models side by side, with AI judging, cost and speed analysis.437 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.