Lorikeet CX + AI Jobs Board MCP server

{"additionalProperties":true,"properties":{"context":{"description":"Explain whyin you15-25 arewords, callingin third person, why this tool is called and how it fits intosupports the user's overall goal. ThisFor parameteranalytics isonly. usedYou forMUST analyticsdescribe andonly userthe intentabstract tracking.purpose YOUof MUSTthe providetool 15-25call. wordsNEVER (countinclude, carefully).repeat, NEVERparaphrase, useor firstinfer personpersonal, ('I'sensitive, 'we'or identifying information from the user request or tool results, 'you')including -names, maintainemails, third-personphone perspective.numbers, NEVERIPs, includeIDs, sensitiveor informationcredentials. You MUST generalize specific entities into roles such as credentials\"a user\", passwords\"the customer\", or personal\"an data.account\". Example (20 words): \"SearchingRetrieving acrossa thecustomer's organization'srecent repositoriesorders to findinvestigate alla openbilling issuesissue relatedand tohelp performancesupport complaintsdetermine the appropriate resolution.\"","type":"string"},"conversation_id":{"description":"Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and latencydo issuesnot issue parallel tool calls until you have it.","type":"string"},"llm_model":{"description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for teamanalytics prioritization.\only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.","type":"string"}},"required":["context","llm_model"],"type":"object"}

{"additionalProperties":true,"properties":{"context":{"description":"Explain whyin you15-25 arewords, callingin third person, why this tool is called and how it fits intosupports the user's overall goal. ThisFor parameteranalytics isonly. usedYou forMUST analyticsdescribe andonly userthe intentabstract tracking.purpose YOUof MUSTthe providetool 15-25call. wordsNEVER (countinclude, carefully).repeat, NEVERparaphrase, useor firstinfer personpersonal, ('I'sensitive, 'we'or identifying information from the user request or tool results, 'you')including -names, maintainemails, third-personphone perspective.numbers, NEVERIPs, includeIDs, sensitiveor informationcredentials. You MUST generalize specific entities into roles such as credentials\"a user\", passwords\"the customer\", or personal\"an data.account\". Example (20 words): \"SearchingRetrieving acrossa thecustomer's organization'srecent repositoriesorders to findinvestigate alla openbilling issuesissue relatedand tohelp performancesupport complaintsdetermine the appropriate resolution.\"","type":"string"},"conversation_id":{"description":"Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and latencydo issuesnot issue parallel tool calls until you have it.","type":"string"},"llm_model":{"description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for teamanalytics prioritization.\only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.","type":"string"},"slug":{"type":"string"}},"required":["slug","context","llm_model"],"type":"object"}

{"additionalProperties":true,"properties":{"context":{"description":"Explain whyin you15-25 arewords, callingin third person, why this tool is called and how it fits intosupports the user's overall goal. ThisFor parameteranalytics isonly. usedYou forMUST analyticsdescribe andonly userthe intentabstract tracking.purpose YOUof MUSTthe providetool 15-25call. wordsNEVER (countinclude, carefully).repeat, NEVERparaphrase, useor firstinfer personpersonal, ('I'sensitive, 'we'or identifying information from the user request or tool results, 'you')including -names, maintainemails, third-personphone perspective.numbers, NEVERIPs, includeIDs, sensitiveor informationcredentials. You MUST generalize specific entities into roles such as credentials\"a user\", passwords\"the customer\", or personal\"an data.account\". Example (20 words): \"SearchingRetrieving acrossa thecustomer's organization'srecent repositoriesorders to findinvestigate alla openbilling issuesissue relatedand tohelp performancesupport complaintsdetermine the appropriate resolution.\"","type":"string"},"conversation_id":{"description":"Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and latencydo issuesnot issue parallel tool calls until you have it.","type":"string"},"llm_model":{"description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for teamanalytics prioritization.\only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.","type":"string"}},"required":["context","llm_model"],"type":"object"}

{"additionalProperties":true,"properties":{"context":{"description":"Explain whyin you15-25 arewords, callingin third person, why this tool is called and how it fits intosupports the user's overall goal. ThisFor parameteranalytics isonly. usedYou forMUST analyticsdescribe andonly userthe intentabstract tracking.purpose YOUof MUSTthe providetool 15-25call. wordsNEVER (countinclude, carefully).repeat, NEVERparaphrase, useor firstinfer personpersonal, ('I'sensitive, 'we'or identifying information from the user request or tool results, 'you')including -names, maintainemails, third-personphone perspective.numbers, NEVERIPs, includeIDs, sensitiveor informationcredentials. You MUST generalize specific entities into roles such as credentials\"a user\", passwords\"the customer\", or personal\"an data.account\". Example (20 words): \"SearchingRetrieving acrossa thecustomer's organization'srecent repositoriesorders to findinvestigate alla openbilling issuesissue relatedand tohelp performancesupport complaintsdetermine the appropriate resolution.\"","type":"string"},"conversation_id":{"description":"Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and latencydo issuesnot forissue teamparallel prioritization.\"tool calls until you have it.","type":"string"},"limit":{"type":"number"},"llm_model":{"description":"The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. \"claude-opus-4-8\", \"gpt-5.2\"). Used for analytics only. If you do not know your model identifier with certainty, pass \"unknown\" — never guess.","type":"string"},"pillar":{"enum":["Support","Retention" ⟨22 unchanged words⟩ type":"string"}},"required":["context","llm_model"],"type":"object"}