Skip to main content
Glama
Moe03

Convocore MCP Server

by Moe03
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

create_agent_from_template

Create chat and voice agents from a predefined template with workspace context, knowledge base, lead funnel, and optional web search.

Instructions

PRIMARY way to create chat+voice agents. Workspace is resolved internally from MCP configuration/workspace secret context (no workspaceId input). Uses strict template invariants: agentPlatform=vg, enableNodes=true, vg_enableUIEngine=true, vg_enableUIEngineForms=true + form notify, default funnelConfig (lead scoring + email notify), nodes[0].kb.enabled (auto RAG, maxChunks=3, vgOptions.maxChunkSize=512), nodes[0].toolsIds includes built-in web-search, chat model always claude-haiku-4-5-20251001 (Claude Haiku 4.5), standard prompt clauses. vg_* overrides blocked from additionalConfig. NON-SALES agents (registration, internal, support-only): pass leadCapture=false and appendStandardPromptClauses=false (and attachWebSearchTool=false if it must not browse) so no sales text, funnel or lead forms are added. CRITICAL: bake scraped ground-truth AND a labeled image catalog (after read_image on real photos) into systemPrompt — KB alone is not enough. Pass ownerNotifyEmails so the funnel can email sales. Do NOT invent HTTP notify-sales webhooks. Run 8–12 turn tests before declaring done. Response includes prototypeUrl / tryItUrl — ALWAYS paste that link for the user to try the agent. Pattern: https://app.convocore.ai/{eu|na}/prototype/{agentId}. NEVER invent app.convocore.ai/agents/...

Input Schema

NameRequiredDescriptionDefault
urlNoBackward-compatible alias for sourceUrl.
imageNoBackward-compatible alias for widgetImageUrl.
titleNoAgent title
modelIdNoOverride chat model. Default claude-haiku-4-5-20251001 (Claude Haiku 4.5); omit unless the user asks for another model.
brandingNo
languageNoBackward-compatible alias for defaultLanguage.
templateNoBackward-compatible field currently ignored.
chatBgURLNo
requestIdNoOptional idempotency key. Reusing the same requestId returns the already-created agent instead of creating a duplicate.
sourceUrlNoOptional — MCP waits for scrape (for KB / context). Not required to create the agent.
themeTypeNoWidget theme (default light unless user wants dark)
descriptionNoShort description
leadCaptureNoDefault true: installs the default lead funnel, lead collection rules and lead forms. Set false for non-sales agents (registration bots, internal assistants).
voiceConfigNoFull voice configuration. speechGen.provider MUST be `google-live` or `ultravox`. Use search_voices on those providers only.
voicePromptNoOptional Gemini Live systemInstruction text. If omitted, systemPrompt is used for voice as well.
funnelConfigNoAI Funnel & Lead Scoring (built-in). Use this instead of a custom HTTP “notify sales team” webhook. enabled + steps (id/name/description/condition/points/category) + notificationRules (type score_threshold|steps_completed|data_collected, recipients emails, cooldownStrategy). Runtime scores the conversation and emails recipients when a rule fires.
primaryColorNoHex brand colour, e.g. #226D7A (from scrape_url colour list).
systemPromptNoMain chat / node instructions → nodes[0].instructions only. Do not send vg_instructions.
enableAutoRagNoDefault true: start node auto-retrieves KB chunks.
createKbUrlDocNoIf true with sourceUrl, attach URL KB after create (errors are non-fatal).
widgetImageUrlNoWidget assistant avatar/logo URL (favicon from scrape_url is ideal).
defaultLanguageNoDefault language for the agent. Must be a single language code/name (never "multilingual"). Default: "en".
roundedImageURLNoBackward-compatible alias for image.
additionalConfigNoExtra agent fields, same as update_agent additionalConfig; merged last with safeguards (keys starting with vg_ and core template keys are ignored). Fields: roundedImageURL, branding, customThemeJSONString, chatBgURL, lang, fontFamily, rectangeImageURL, avatarImageUrl, headerImageUrl, bannerImageUrl, enableNodes, nodesSettings, vg_systemPrompt, vg_initPrompt, vg_initMessages, vg_prompt, vg_temperature, vg_defaultModel, vg_maxTokens, vg_max_messages_history, vg_enableAboutContext, ifKnowsThreshold, enableFallback, fallbackSettings, enableAudioSupport, captureIGStories, metaHumanTakeover, vg_kb_llm, vg_kbDefaultDimension, vg_kbTopChunks, vg_kbCharCount, vg_kbDocsNum, proactiveMessage, autoStartWidget, messageDelayMS, scrollAnimation, disableSmoothScroll, buttonsLayout, buttonVariant, inputVariant, ui, ADVANCED_customCSS, disableRating, chatEndMessage, aiIntroductionMessage, enableAIIntroductionMessage, privacyDisclaimer, gdprCompliance, disableModelAutoUpgrade, acceptFileUpload, disableFileUpload, enableQuickFileUpload, soundEffectUrl, soundEffectEnabled, agentPlatform, AITranslateTo, enableAITranslate, disableHumanHandoff, alwaysShowHandoff, manualControl, enableVGHandoff, fixedHandoffPopup, UIhandoffTitle, UIhandoffSubtitle, showHandoffEvenIfOffline, persistHandoffOnRefresh, blockInputDuringHandoffRequest, disableHandoffMessages, handoffNowChattingMessage, handoffBackToAiMessage, handoffCancelButtonLabel, disableHandoffStatusMessages, convoTags, topicsConfig, starred, enableGeoAnalytics, hideVoiceflowAnalytics, hideCallAnalytics, hideConversationMetrics, hideCustomAnalytics, hideVapiAnalytics, hideFunnelAnalytics, marketplace, autoTest, customButtonJSON_STRING.
proactiveMessageNoWidget greeting bubble
ownerNotifyEmailsNoSales/owner emails. Used for form notify AND funnelConfig.notificationRules. Required for email alerts on hot leads. Do NOT create a custom HTTP webhook for this.
attachWebSearchToolNoDefault true: attaches built-in web-search to the start node. Set false for agents that must not search the web.
leadCollectionRulesNoWhen to persist a CRM lead. Default: collect when email, phone, or phone_number is present.
appendStandardPromptClausesNoDefault true: appends anti-repetition, lead-capture, knowledge-source, web-search, pricing and photo clauses to systemPrompt. Set false to store systemPrompt exactly as given (use for non-sales agents).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.6.17

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare openWorldHint=true and destructive=false, but the description adds substantial behavior: workspace resolution, the strict template invariants, that vg_* overrides are blocked from additionalConfig, the fixed model, and that the response includes prototypeUrl/tryItUrl with a URL pattern. This is rich context beyond annotations, though it doesn't state auth/rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the key purpose, but the paragraph is dense and sprawling, bundling invariants, defaults, testing guidance, and URL rules into one long block. Every sentence is substantive but the lack of structure makes it hard to scan.

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

Completeness5/5

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

For a 29-param creation tool with no output schema, the description covers the important gaps: where the workspace comes from, what the response returns (prototypeUrl/tryItUrl) and its URL pattern, and defaults for the key toggles. An agent can invoke this correctly from the definition alone.

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

Parameters4/5

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

Schema coverage is already 93%, but the description adds real meaning: default behaviors for leadCapture, appendStandardPromptClauses, attachWebSearchTool, ownerNotifyEmails usage, and the fixed chat model. It goes beyond restating schema, though not every one of the 29 params is addressed in prose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource+scope: 'PRIMARY way to create chat+voice agents.' The word 'PRIMARY' implicitly distinguishes it from the sibling create_agent, and the following sentence pins down that workspace is resolved internally, clarifying the creation model.

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

Usage Guidelines5/5

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

Explicitly states when to use the non-sales path (leadCapture=false, appendStandardPromptClauses=false, attachWebSearchTool=false) with reasoning, and warns against inventing HTTP notify-sales webhooks. It also routes the agent to read_image for the image catalog and mandates tests before declaring done.

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

Deploy Server

Other Tools