polyglot-ai-workspace

endpoint

https://br-steep-leaf-ae2o29qz-mcp.compute.c-2.us-east-2.aws.neon.tech/mcp

protocol

streamable-http ·2025-06-18

authentication

none observed

public key

none — nobody has proven they own this listing · is it yours? claim it

karma

0 · newcomer

Is polyglot-ai-workspace live?

Yes — it answered the hub's last check (checked 3h ago). It answered 100% of checks over the last 30 days.

Is polyglot-ai-workspace free to use?

Yes — the hub reached it with no key and no payment.

What tools does polyglot-ai-workspace have?

15 tools: build_prompt, transcribe_audio, translate_text, localize_text, get_template, detect_language, validate_custom_model, prepare_compare, ….

Is polyglot-ai-workspace safe to connect?

The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

• get_subscription_status reads open 35d ago

  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.

  mcp-tool

  12345

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {}
  }

  arguments 5 lines copy
• get_custom_model_capabilities reads open 35d ago

  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.

  mcp-tool

  12345

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {}
  }

  arguments 5 lines copy
• get_language_options reads open 35d ago

  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.

  mcp-tool

  12345678910111213

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {
      "uiLanguage": {
        "type": "string",
        "default": "EN",
        "maxLength": 80,
        "description": "UI language code or name such as EN, es or Arabic; defaults to EN."
      }
    },
    "additionalProperties": false
  }

  arguments 13 lines copy
• search_templates reads open 35d ago

  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. Expired accounts see locked Pro template cards. Selecting one returns a paywall, not Pro fields or prompt text. Searching is read-only and does not trigger a send or trial.

  mcp-tool

  123456789101112131415161718192021222324252627282930313233343536373839

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {
      "goal": {
        "type": "string",
        "maxLength": 80,
        "description": "Optional intended outcome, e.g. write a help article."
      },
      "plan": {
        "enum": [
          "free",
          "pro"
        ],
        "type": "string",
        "description": "Filter catalog by free or Pro tier; filtering does not grant access."
      },
      "limit": {
        "type": "integer",
        "default": 12,
        "maximum": 24,
        "minimum": 1,
        "description": "Maximum matches to return (1 to 24), default 12."
      },
      "query": {
        "type": "string",
        "default": "",
        "maxLength": 200,
        "description": "Search phrase or topic; blank lists available templates."
      },
      "uiLanguage": {
        "type": "string",
        "default": "EN",
        "maxLength": 80,
        "description": "Language code for localized template labels; defaults to EN."
      }
    },
    "additionalProperties": false
  }

  arguments 39 lines copy
• open_workspace reads open 35d ago

  Open the embedded Poly-Glot prompt workspace and template browser, optionally prefiltered by a query and translated via uiLanguage. Returns free and locked Pro template cards after trial expiry, plus entitlement and localization. Browsing is read-only and does not start the trial or use a send.

  mcp-tool

  12345678910111213141516171819

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {
      "query": {
        "type": "string",
        "default": "",
        "maxLength": 200,
        "description": "Optional keyword or goal for template search, e.g. resume. Maximum 200 characters."
      },
      "uiLanguage": {
        "type": "string",
        "default": "EN",
        "maxLength": 80,
        "description": "UI language name or code for template labels; defaults to EN."
      }
    },
    "additionalProperties": false
  }

  arguments 19 lines copy
• build_prompt changes data unknown never probed

  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.

  mcp-tool

  12345678910111213141516171819202122232425262728293031323334353637383940414243444546

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "name"
    ],
    "properties": {
      "name": {
        "type": "string",
        "maxLength": 200,
        "minLength": 1,
        "description": "Required accessible template name; use search_templates or get_template to find it."
      },
      "values": {
        "type": "object",
        "default": {},
        "description": "Map of template placeholder names to strings, numbers or booleans, e.g. {topic: onboarding}.",
        "additionalProperties": {
          "type": [
            "string",
            "number",
            "boolean"
          ]
        }
      },
      "uiLanguage": {
        "type": "string",
        "default": "EN",
        "maxLength": 80,
        "description": "Interface language name or code, e.g. EN; independent of source and response languages."
      },
      "inputLanguage": {
        "type": "string",
        "default": "EN",
        "maxLength": 80,
        "description": "Language name or code of input text, e.g. es; defaults to EN."
      },
      "outputLanguage": {
        "type": "string",
        "default": "EN",
        "maxLength": 80,
        "description": "Requested output language name or code, e.g. fr; defaults to EN."
      }
    },
    "additionalProperties": false
  }

  arguments 46 lines copy
• transcribe_audio reads unknown never probed

  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.

  mcp-tool

  123456789101112131415161718192021222324252627282930313233343536

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {
      "prompt": {
        "type": "string",
        "description": "Optional recognition context, such as expected names or specialist vocabulary; not the text to transcribe."
      },
      "audioUrl": {
        "type": "string",
        "format": "uri",
        "description": "Public HTTPS URL of an audio recording to transcribe. Use this OR audioBase64, never both; private or local URLs are not supported."
      },
      "filename": {
        "type": "string",
        "description": "Original audio filename with extension, such as meeting.m4a, to help determine the format."
      },
      "mimeType": {
        "type": "string",
        "description": "Audio MIME type, such as audio/mpeg, audio/mp4, or audio/wav. Recommended for base64 input."
      },
      "audioBase64": {
        "type": "string",
        "description": "Base64-encoded audio bytes, without a data: prefix. Alternative to audioUrl; provide exactly one audio source."
      },
      "languageHint": {
        "type": "string",
        "description": "Optional language hint for speech recognition, such as en, es, or fr. Leave blank if unknown."
      },
      "detectLanguage": {
        "type": "boolean",
        "description": "When true, also infer a supported Poly-Glot language from the resulting transcript; defaults to false."
      }
    },
    "additionalProperties": false
  }

  arguments 36 lines copy
• translate_text reads unknown never probed

  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.

  mcp-tool

  1234567891011121314151617181920212223242526

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "text",
      "targetLanguage"
    ],
    "properties": {
      "text": {
        "type": "string",
        "minLength": 1,
        "description": "Nonempty original text to translate, including any formatting to preserve."
      },
      "sourceLanguage": {
        "type": "string",
        "default": "auto",
        "description": "Original language name or code, such as 'en' or 'English'; 'auto' (default) asks the provider to detect it."
      },
      "targetLanguage": {
        "type": "string",
        "minLength": 1,
        "description": "Required desired output language name or code among the 38 supported, e.g. 'Spanish' or 'es'."
      }
    },
    "additionalProperties": false
  }

  arguments 26 lines copy
• localize_text reads unknown never probed

  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.

  mcp-tool

  123456789101112131415161718192021222324252627282930313233

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "text",
      "targetLanguage"
    ],
    "properties": {
      "text": {
        "type": "string",
        "minLength": 1,
        "description": "Original nonempty copy to adapt for the target culture, region, and audience."
      },
      "tone": {
        "type": "string",
        "description": "Desired writing style, such as 'friendly', 'formal', or 'concise'."
      },
      "locale": {
        "type": "string",
        "description": "Optional regional locale, such as 'es-MX', 'fr-CA', or 'en-GB'; affects regional spelling and conventions."
      },
      "audience": {
        "type": "string",
        "description": "Intended readers or customers, e.g. 'first-time mobile app users' or 'enterprise developers'."
      },
      "targetLanguage": {
        "type": "string",
        "minLength": 1,
        "description": "Required output language name or code, e.g. 'Arabic' or 'ar'."
      }
    },
    "additionalProperties": false
  }

  arguments 33 lines copy
• get_template reads unknown 35d ago

  Retrieve a named template's fields and entitled prompt body. Use search_templates first to find the exact name; inaccessible templates return a paywall view without Pro fields or prompt content after the trial. Returns template, entitlement and localization data. Reading a template alone neither starts the trial nor consumes a send.

  mcp-tool

  12345678910111213141516171819202122

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "name"
    ],
    "properties": {
      "name": {
        "type": "string",
        "maxLength": 200,
        "minLength": 1,
        "description": "Required template name returned by search_templates."
      },
      "uiLanguage": {
        "type": "string",
        "default": "EN",
        "maxLength": 80,
        "description": "Language code for localized template fields; defaults to EN."
      }
    },
    "additionalProperties": false
  }

  arguments 22 lines copy
• detect_language reads unknown never probed

  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.

  mcp-tool

  123456789101112131415

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "text"
    ],
    "properties": {
      "text": {
        "type": "string",
        "minLength": 1,
        "description": "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."
      }
    },
    "additionalProperties": false
  }

  arguments 15 lines copy
• validate_custom_model reads unknown 35d ago

  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.

  mcp-tool

  1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "adapterMode"
    ],
    "properties": {
      "model": {
        "type": "string",
        "default": "",
        "maxLength": 200,
        "description": "Optional external model identifier for a test probe."
      },
      "probe": {
        "type": "boolean",
        "default": false,
        "description": "True sends a minimal external request to test the model; false only checks URL safety."
      },
      "apiKey": {
        "type": "string",
        "maxLength": 2000,
        "description": "Optional transient API credential, never stored or echoed."
      },
      "baseUrl": {
        "type": "string",
        "maxLength": 2000,
        "description": "Public HTTPS base URL for openai-compatible mode."
      },
      "authMode": {
        "enum": [
          "bearer",
          "api-key-header",
          "none"
        ],
        "type": "string",
        "default": "bearer",
        "description": "Custom REST authentication method: bearer, API-key header, or none."
      },
      "endpoint": {
        "type": "string",
        "maxLength": 2000,
        "description": "Full public HTTPS URL for custom-rest mode."
      },
      "adapterMode": {
        "enum": [
          "openai-compatible",
          "custom-rest"
        ],
        "type": "string",
        "description": "Adapter: openai-compatible or custom-rest."
      },
      "promptField": {
        "type": "string",
        "default": "prompt",
        "maxLength": 100,
        "description": "JSON request field for test prompt content on custom REST endpoints."
      },
      "systemField": {
        "type": "string",
        "default": "system",
        "maxLength": 100,
        "description": "JSON request field for system instructions on custom REST endpoints."
      },
      "apiKeyHeader": {
        "type": "string",
        "default": "x-api-key",
        "maxLength": 100,
        "description": "Header name when using api-key-header authentication."
      },
      "responseTextPath": {
        "type": "string",
        "maxLength": 200,
        "description": "JSON response field or path holding the generated text."
      }
    },
    "additionalProperties": false
  }

  arguments 77 lines copy
• prepare_compare changes data unknown never probed

  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.

  mcp-tool

  12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {
      "name": {
        "type": "string",
        "maxLength": 200,
        "minLength": 1,
        "description": "Optional accessible template name; supply this or a raw prompt."
      },
      "prompt": {
        "type": "string",
        "maxLength": 30000,
        "minLength": 1,
        "description": "Optional original prompt for each provider, maximum 30,000 characters; provide this or name."
      },
      "values": {
        "type": "object",
        "default": {},
        "description": "Placeholder values used when preparing a named template.",
        "additionalProperties": {
          "type": [
            "string",
            "number",
            "boolean"
          ]
        }
      },
      "providers": {
        "type": "array",
        "items": {
          "enum": [
            "chatgpt",
            "claude",
            "gemini",
            "perplexity",
            "grok",
            "copilot",
            "mistral",
            "huggingchat",
            "duckduckgo"
          ],
          "type": "string"
        },
        "default": [
          "chatgpt",
          "claude"
        ],
        "maxItems": 9,
        "minItems": 2,
        "description": "Two to nine provider IDs; defaults to ChatGPT and Claude and duplicates are removed."
      },
      "uiLanguage": {
        "type": "string",
        "default": "EN",
        "maxLength": 80,
        "description": "Interface language name or code, e.g. EN; independent of source and response languages."
      },
      "inputLanguage": {
        "type": "string",
        "default": "EN",
        "maxLength": 80,
        "description": "Language name or code of input text, e.g. es; defaults to EN."
      },
      "outputLanguage": {
        "type": "string",
        "default": "EN",
        "maxLength": 80,
        "description": "Requested output language name or code, e.g. fr; defaults to EN."
      }
    },
    "additionalProperties": false
  }

  arguments 73 lines copy
• prepare_custom_compare reads unknown never probed

  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.

  mcp-tool

  1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "prompt",
      "customModels"
    ],
    "properties": {
      "prompt": {
        "type": "string",
        "maxLength": 30000,
        "minLength": 1,
        "description": "Required canonical prompt shared among all selected models, up to 30,000 characters."
      },
      "uiLanguage": {
        "type": "string",
        "default": "EN",
        "maxLength": 80,
        "description": "Interface language name or code, e.g. EN; independent of source and response languages."
      },
      "customModels": {
        "type": "array",
        "items": {
          "type": "object",
          "required": [
            "label",
            "adapterMode"
          ],
          "properties": {
            "label": {
              "type": "string",
              "maxLength": 100,
              "description": "Human-readable name of the custom model in the comparison results."
            },
            "model": {
              "type": "string",
              "maxLength": 200,
              "description": "Optional external model identifier."
            },
            "baseUrl": {
              "type": "string",
              "maxLength": 2000,
              "description": "Public HTTPS base URL for an OpenAI-compatible model."
            },
            "endpoint": {
              "type": "string",
              "maxLength": 2000,
              "description": "Public HTTPS inference URL for a custom REST model."
            },
            "adapterMode": {
              "enum": [
                "openai-compatible",
                "custom-rest"
              ],
              "type": "string",
              "description": "Adapter type for this model's API."
            }
          },
          "additionalProperties": false
        },
        "maxItems": 5,
        "minItems": 1,
        "description": "Required array of 1 to 5 custom model connection descriptors; excludes authentication credentials."
      },
      "inputLanguage": {
        "type": "string",
        "default": "EN",
        "maxLength": 80,
        "description": "Language name or code of input text, e.g. es; defaults to EN."
      },
      "outputLanguage": {
        "type": "string",
        "default": "EN",
        "maxLength": 80,
        "description": "Requested output language name or code, e.g. fr; defaults to EN."
      },
      "builtinProviders": {
        "type": "array",
        "items": {
          "enum": [
            "chatgpt",
            "claude",
            "gemini",
            "perplexity",
            "grok",
            "copilot",
            "mistral",
            "huggingchat",
            "duckduckgo"
          ],
          "type": "string"
        },
        "default": [],
        "description": "Optional built-in provider IDs to include alongside custom targets. This preparation tool does not call providers."
      }
    },
    "additionalProperties": false
  }

  arguments 98 lines copy
• run_custom_model unknown never probed

  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.

  mcp-tool

  123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122

  {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "adapterMode",
      "prompt"
    ],
    "properties": {
      "model": {
        "type": "string",
        "default": "",
        "maxLength": 200,
        "description": "Model identifier at the custom provider, when needed."
      },
      "apiKey": {
        "type": "string",
        "maxLength": 2000,
        "description": "Transient authentication key sent to the chosen provider; never log or embed in prompts."
      },
      "prompt": {
        "type": "string",
        "maxLength": 30000,
        "minLength": 1,
        "description": "Required nonempty prompt to send externally, maximum 30,000 characters."
      },
      "system": {
        "type": "string",
        "maxLength": 10000,
        "description": "Optional system instructions supported by the endpoint."
      },
      "baseUrl": {
        "type": "string",
        "maxLength": 2000,
        "description": "Required public HTTPS base URL for openai-compatible mode."
      },
      "authMode": {
        "enum": [
          "bearer",
          "api-key-header",
          "none"
        ],
        "type": "string",
        "default": "bearer",
        "description": "Custom REST authentication mode, default bearer."
      },
      "endpoint": {
        "type": "string",
        "maxLength": 2000,
        "description": "Required public HTTPS inference URL for custom-rest mode."
      },
      "maxTokens": {
        "type": "integer",
        "maximum": 128000,
        "minimum": 1,
        "description": "Optional maximum output token count, subject to model limits."
      },
      "uiLanguage": {
        "type": "string",
        "default": "EN",
        "maxLength": 80,
        "description": "Interface language name or code, e.g. EN; independent of source and response languages."
      },
      "adapterMode": {
        "enum": [
          "openai-compatible",
          "custom-rest"
        ],
        "type": "string",
        "description": "Adapter for the target endpoint: openai-compatible or custom-rest."
      },
      "promptField": {
        "type": "string",
        "default": "prompt",
        "maxLength": 100,
        "description": "Custom REST request JSON key for prompt content."
      },
      "systemField": {
        "type": "string",
        "default": "system",
        "maxLength": 100,
        "description": "Custom REST request JSON key for system instructions."
      },
      "temperature": {
        "type": "number",
        "maximum": 2,
        "minimum": 0,
        "description": "Optional response sampling randomness between 0 and 2."
      },
      "apiKeyHeader": {
        "type": "string",
        "default": "x-api-key",
        "maxLength": 100,
        "description": "Custom REST API-key authentication header name."
      },
      "extraHeaders": {
        "type": "object",
        "default": {},
        "description": "Extra HTTP headers required by the provider, if any.",
        "additionalProperties": {
          "type": "string"
        }
      },
      "inputLanguage": {
        "type": "string",
        "default": "EN",
        "maxLength": 80,
        "description": "Language name or code of input text, e.g. es; defaults to EN."
      },
      "outputLanguage": {
        "type": "string",
        "default": "EN",
        "maxLength": 80,
        "description": "Requested output language name or code, e.g. fr; defaults to EN."
      },
      "responseTextPath": {
        "type": "string",
        "maxLength": 200,
        "description": "Optional JSON response field/path containing generated text."
      }
    },
    "additionalProperties": false
  }

  arguments 122 lines copy

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.

Served from the same domain, which is what was measured. Not a claim that one owner runs them: ownership is what a passport proves, and each of these says for itself.

• br-shiny-salad-baig3dad-api.compute.c-8.eu-central-1.aws.neon.tech agent-therapy mcp · 9 tools
• mcp.neon.tech mcp.neon.tech mcp · 0 tools