Index / Verified tools / AI models and embeddings

AI models and embeddings

Inference, embeddings and prompt execution. Every tool below was read from that server's own tools/list, so the name and arguments are what the server exposes, not what its description claims.

ToolServer
llm-proxyanswers
PAID MCP TOOL — $0.021 USDC per successful call via native x402. Discovery is free. LLM inference proxy — pay USDC, get AI responses without managing API keys. Accepts a prompt and optional system instruction, forward...
arguments: prompt, system, model, max_tokens
The Stall
ai.intuitek.the-stall
estimate_llm_costanswers
Estimate the cost of an LLM/API workload (input + output tokens) for a usage-priced provider (OpenAI, Anthropic, AWS Bedrock…) from its real rate card.
arguments: slug, model, inputTokens, outputTokens
CostBench
com.costbench
read_llm_discoveryanswers
Read-only fetch of an IntoDNS.ai LLM/agent discovery file: llms.txt (canonical agent index), llms-full.txt (full prompt-ready context), llms.json (structured prompt routing), llm/api.md (Markdown API guide), openapi.j...
arguments: file
IntoDNS.ai DNS & Email Security Scanner
ai.intodns
llmanswers
Ask a DIFFERENT LLM a question and get its answer, billed per token from the Vaaya wallet (model cost + 3%, usually a fraction of a cent). Use it to get a second opinion from a rival model, cross-check an answer, summ...
arguments: prompt, model, system, max_tokens
Vaaya
ai.vaaya
detect_prompt_injectionanswers
Classify a prompt before it reaches your LLM. Brainiall Prompt Shield engine. Returns category (jailbreak | prompt_injection | data_exfiltration | impersonation | none), severity, reason, confidence.
arguments: prompt
Brainiall NLP
com.brainiall
prompt_caching_savings_calculatoranswers
Prompt Caching Savings Calculator (LLM API Costs) — Estimate how much prompt caching cuts your LLM API bill: monthly input tokens, cacheable share, and hit rate give per-model savings, cache writes included.
arguments: monthlyInputTokensM, cacheableSharePct, hitRatePct, modelId
com.calcfleet/calculators
com.calcfleet
promptfoo_importanswers
Import a promptfooconfig.yaml. Creates a prompt, a dataset from the test vars, and metrics from the assert blocks (llm-rubric/g-eval become judge metrics; contains/equals/regex/is-json become deterministic check metri...
arguments: config
CompletionKit
com.completionkit
update_segment_promptsanswers
Set one segment's final prompts VERBATIM — no LLM rewrite. The direct counterpart to update_segment_content: your text is written as-is to the segment's creative direction and to the matching asset configs the...
arguments: project_id, segment_number, image_prompt, start_frame_prompt, video_prompt, media_queries
framesail
com.framesail
agentllm_micro
OpenAI-compatible AgentLLM Micro text inference for classification, extraction, routing and short summaries. Run prepare_agentllm_micro with the identical arguments first. Hard limits: 2,400 UTF-8 input bytes, 8 messa...
arguments: prompt, system, max_tokens
EU Compliance Tools (pay-per-call, x402)
io.github.patrickpi1312
chat_completionanswers
Send a conversation to any text model available through CCAPI (Claude, GPT, Gemini, DeepSeek, GLM, MiniMax, Kimi, Qwen…) and get the reply. Useful for consulting a second model for a different perspective, running a c...
arguments: model, messages, max_tokens, temperature, top_p, stop
CCAPI
ai.ccapi
search_promptsanswers
Search the PromptSharp prompt library. Returns ready-to-run AI prompts scoped to your license tier (no token = 15 public teasers; vertical Pro = your vertical; all-access = the full cross-vertical library). Locked res...
arguments: query, vertical, section, limit
ai.promptsharp/promptsharp
ai.promptsharp
get_promptanswers
Fetch one prompt by id: the full copy-paste prompt plus its guardrails and a why-it-works note. Requires that the prompt is within your license scope.
arguments: id
ai.promptsharp/promptsharp
ai.promptsharp
promptarch_lint_artifactanswers
Lint an AI agent context file (CLAUDE.md, AGENTS.md, Cursor rules, Copilot instructions, memory files) with PromptArch's deterministic linter: ~30 research-backed rule families covering current-model anti-patterns (to...
arguments: content, format, filename
ai.promptarch/mcp
ai.promptarch
promptarch_list_artifact_typesanswers
List the artifact types promptarch_generate_artifact can produce from a project description.
ai.promptarch/mcp
ai.promptarch
promptarch_generate_artifactanswers
Generate an AI agent context artifact (e.g. context_pack, claude_md) from a project description. Requires a PromptArch API key configured as an Authorization: Bearer pk_... header on this MCP server. Consumes credits.
arguments: artifact, project_name, project_description, tech_stack, repo_structure, commands
ai.promptarch/mcp
ai.promptarch
video_to_promptanswers
Turn one of your finished Video Analysis reports into ONE reusable generation prompt that recreates the source video's look, energy, pacing and mood, with a {your photo} placeholder where your own subject goes. Pass r...
arguments: report_id, video_url, mode, engine
ai.switchapp/switch
ai.switchapp
thinkneo_optimize_promptanswers
Analyze prompt and suggest optimizations with live metrics context.
arguments: prompt
ThinkNEO Control Plane
ai.thinkneo
get_analyst_configanswers
Returns the TunnelMind analyst config bundle. Configures any LLM (Claude, GPT, Gemini, local) to behave as a TunnelMind analyst that knows the data graph, follows the 5-call golden path, and surfaces attestation_tier ...
arguments: surface, version, receipt
TunnelMind Data API
ai.tunnelmind
generate_llms_txtanswers
Generate llms.txt and llms-full.txt for a site, following the llmstxt.org convention. Inventories the site from its robots.txt, sitemaps, and homepage links, then writes an index file and a full file with page content...
arguments: url, refresh
Superflow Free Tools
ai.usesuperflow
build_avatar_promptanswers
Build a highly detailed prompt for generating a unique reusable avatar/model. Use this when the user wants help describing a person before image generation. If the user's prompt is already intentional and specific, Uw...
arguments: user_text, model_slug, camera, camera_label, aspect_ratio
Uwear
ai.uwear
llm_modelsanswers
List available text-generation LLM models with per-token pricing and max context. 텍스트 생성 모델 카탈로그를 반환합니다. 각 모델의 1M 토큰당 input/output 단가(포인트), 계열·크기·멀티모달 여부·태그·추천 용도(use_cases)·max_context 를 한 응답에 포함합니다. llm_chat Tool의 m...
arguments: family, tag, use_case, multimodal
APICK AI
app.apick
llm_chatanswers
Send a chat request to a selected LLM model and receive the assistant reply. 선택한 LLM 모델에 대화를 보내고 assistant 응답을 받습니다. 서버는 대화 히스토리를 보관하지 않는 stateless 방식 — 매 호출마다 전체 히스토리를 messages 로 전송하고, 응답의 compacted_messages 를 다음 턴의 ...
arguments: model, messages, content, system, compact, temperature
APICK AI
app.apick
send_script_to_teleprompteranswers
Turn one or more finished video scripts into a single one-tap link that opens the user's Daily Studio app with the script(s) loaded into the teleprompter and the right platform safe-zones selected, ready to record. Fo...
arguments: text, title, wpm, platform, scripts
Daily Studio Teleprompter
app.dailystudio
get_battle_promptanswers
Reveal the challenge after register_for_battle. Returns prompt, rules, output_format, max_spend_usd, time_limit_minutes, prompt_revealed_at, and deadline_at; reading it starts your deadline clock. Answer locally, then...
arguments: battle_id, registration_id
Agent Coliseum MCP
app.nanocorp.agentarena
get_suggested_promptsanswers
Onboarding suggestion chips for the chat surface — the same 'What's trending?' / 'Find me a gift' / 'Compare products' chips chat.curie.app shows above its input. When called on a per-shop MCP endpoint (e.g. /api/mcp/...
arguments: count, category
Curie Commerce
co.curie
request_job_completionanswers
Prepare a transaction to submit job completion as the assigned agent. Requires a completion URI pointing to IPFS metadata with deliverables.
arguments: jobId, completionURI
AGI Alpha
com.agialpha
architect.validateanswers
Pro/Teams — first-pass doctrine review of agentic code/workflow against the 10-principle Agentic AI Blueprint. ON CLIENT TIMEOUT — DO NOT RETRY THIS TOOL. Long-running LLM call (60-180s typical); MCP clients commonly ...
arguments: implementation_context, focus_area, task, language, repository, files
AI Design Blueprint
com.aidesignblueprint
get_fastest_completion_pathanswers
Find the fastest official way to complete a practical task. Use for requests like “how do I cancel,” “return an item,” “get a refund,” “file a warranty claim,” or “find the official form.” It returns ordered, source-b...
arguments: provider, task, state
taskrail
com.alamavar.taskrail
llm_api_cost_calculatoranswers
LLM API Cost Calculator (GPT-4o, Claude, Gemini) — Estimate monthly API costs for GPT-4o, Claude, and Gemini from tokens per request and volume. See input vs output cost split. Prices as of 2025 — verify.
arguments: model, inputTokensPerReq, outputTokensPerReq, requestsPerMonth
com.calcfleet/calculators
com.calcfleet
llm_self_host_vs_api_calculatoranswers
LLM Self-Host vs API Cost Calculator — Find the monthly token volume where self-hosting an LLM on rented GPUs beats paying per token for an API. Compare costs, GPUs needed, and breakeven point.
arguments: monthlyInputTokensM, monthlyOutputTokensM, apiModelId, gpuId, gpuHourlyUsd, throughputTokensPerSec
com.calcfleet/calculators
com.calcfleet
llm_throughput_calculatoranswers
LLM Throughput & GPU Sizing Calculator — Estimate how many GPUs your LLM needs: concurrent users and target tokens per second become cluster size, monthly cloud cost, and real utilization at load.
arguments: concurrentUsers, targetTokensPerSecPerUser, gpuId, gpuHourlyUsd, aggregateTokensPerSecPerGpu, utilizationHeadroomPct
com.calcfleet/calculators
com.calcfleet
claidex_research_promptanswers
Compose a rigorous, reusable investigation prompt that tells an MCP client which Claidex tools and resources to use.
arguments: objective, target_gene, disease, risk_tolerance
Claidex MCP
com.claidex
rank_documents_by_embeddinganswers
Embed a query and candidate documents, then rank documents by cosine similarity. Use for semantic matching, retrieval checks, clustering triage, and lightweight RAG over user-provided passages.
arguments: query, documents, top_k
Claidex MCP
com.claidex
prompts_listanswers
List all prompts
CompletionKit
com.completionkit
prompts_getanswers
Get a prompt by ID
arguments: id
CompletionKit
com.completionkit
prompts_createanswers
Create a prompt
arguments: name, description, template, llm_model, tag_names
CompletionKit
com.completionkit
prompts_updateanswers
Update a prompt. If the prompt already has runs, this creates a new DRAFT version (current=false) rather than editing in place or publishing — promote it with prompts_publish — so an agent's edits don't go live withou...
arguments: id, name, description, template, llm_model, tag_names
CompletionKit
com.completionkit
prompts_deleteanswers
Delete a prompt
arguments: id
CompletionKit
com.completionkit
prompts_publishanswers
Publish a prompt version, making it the current version
arguments: id
CompletionKit
com.completionkit
prompts_suggest_improvementanswers
Suggest an improved version of a prompt, grounded in a run's test results and judge feedback. Analyzes the run's responses, scores, and reviews, then returns reasoning plus a rewritten template (preserving {{variables...
arguments: run_id
CompletionKit
com.completionkit
dossier_llms_txtanswers
Core dossier check: Detect whether a domain publishes an llms.txt at its root — the emerging convention that gives AI agents a curated markdown index of a site's content. Use in a content-posture audit to confirm a si...
arguments: domain
com.domainposture/mcp
com.domainposture
get_prompt_templateanswers
Return the rendered text of one of this server's guided prompts (mcp-demo-tour, tar-matter-kickoff, weekly-digest). Use when the client can call tools but cannot open MCP prompts directly, or when you want to inspect ...
arguments: prompt_name, audience, matter_description, week_start
eDiscovery Decoder News/Calc
com.ediscoverydecoder
calculate_installmentanswers
Calcula parcelas de financiamento/empréstimo pelo sistema Price (parcelas fixas). Parâmetros obrigatórios: total, installments, monthly_rate. Use exatamente estes nomes, em inglês.
arguments: total, installments, monthly_rate
FalaZuki Finance BR
com.falazuki
get_llms_fullanswers
Return a link to the complete, source-linked agent reference (llms-full.txt) for a product — its entire prose, API surface, and examples in one document. This file is large, so it is returned as a resource link and ca...
arguments: product
com.freebatteryfactory/docs
com.freebatteryfactory
get_llms_txtanswers
Get the auto-generated llms.txt for a cataloged company: a curated, AI-readable guide to the business.
arguments: domain
com.groundedaeo/grounded-aeo
com.groundedaeo
send_quote_completion_linkanswers
Sends a checkout/completion link to the customer for a specific quote (by quote key) via SMS and/or Email. THIS MESSAGES THE CUSTOMER.
arguments: quoteKey, body
HireAHelper Moving Services
com.hireahelper
get_quote_completion_urlanswers
Gets the completion (checkout) URL for a specific quote by quote key, WITHOUT sending an email or SMS to the customer.
arguments: quoteKey
HireAHelper Moving Services
com.hireahelper
get_llms_txtanswers
Fetch /llms.txt (full mirror; optional offset/limit lines)
arguments: offset, limit
ikeytz – Schlüsseldienst Ludwigsburg
com.ikeytz
get_llms_mcp_serveranswers
Fetch /llms-mcp-server.txt — public Server-MCP tool catalog (all tools, how to call, no login).
arguments: offset, limit
ikeytz – Schlüsseldienst Ludwigsburg
com.ikeytz
get_llms_mcp_webanswers
Fetch /llms-mcp-web.txt — public WebMCP (browser) tool catalog (bootstrap + full list, no login).
arguments: offset, limit
ikeytz – Schlüsseldienst Ludwigsburg
com.ikeytz
get_llms_txtanswers
AI-readable overview of the site (llms.txt). Returns: ok.
Invokera Status
com.invokera
post_chat_completionsanswers
Creates a model response for the given chat conversation Billing per call: Credits: metered (~0 avg).
arguments: body
com.jojapi/gpt-5
com.jojapi
post_embeddingsanswers
Creates an embedding vector representing the input text. Group: Embeddings. Billing per call: Credits: metered.
arguments: body
com.jojapi/swift-ai
com.jojapi
generate_elevenlabs_agent_promptanswers
Generates a production-grade system prompt for an ElevenLabs conversational agent acting as a business phone receptionist: identity, job, voice style, booking flow, guardrails, and escalation rules.
arguments: biz, agentName, industry, tasks, hours, spanish
com.lobbyvoices/receptionist-toolkit
com.lobbyvoices
parent_list_enrollmentsanswers
Returns the parent's enrollments (programs their kid is signed up for).
Lodi Kids Activities
com.lodikidsactivities
parent_report_enrollmentanswers
Self-report that the parent enrolled their kid in a program outside the LKA RegFlow ('I'm In'). Accepts program UUID or slug.
arguments: program_id, kid_id
Lodi Kids Activities
com.lodikidsactivities
installment_plananswers
Split a total into an installment schedule with optional deposit. PREMIUM (license). Rounding remainders land on the final payment so the schedule always sums exactly. Typical input {"total": 1000, "installments": 3,...
arguments: total, installments, deposit_pct
Moltline Merchant Maths
com.moltlinestudio
send_quote_completion_linkanswers
Sends a checkout/completion link to the customer for a specific quote (by quote key) via SMS and/or Email. THIS MESSAGES THE CUSTOMER.
arguments: quoteKey, body
MovingPlace Moving Services
com.movingplace
get_quote_completion_urlanswers
Gets the completion (checkout) URL for a specific quote by quote key, WITHOUT sending an email or SMS to the customer.
arguments: quoteKey
MovingPlace Moving Services
com.movingplace
neblla_get_llmsanswers
Fetch the Neblla developer guide (llms.txt), split by topic so you read only what the app uses. Call this BEFORE designing or writing any code for a Neblla app — at minimum the `core` section (the default): the canoni...
arguments: section, offset, maxLength
Neblla
com.neblla
Showing 60 of 169 verified tools. Search the whole set, including full input schemas, at https://neuronto.com/tools?q=..., or connect an agent to https://neuronto.com/mcp and call find_tool. No key, no signup.

"Answers" means the endpoint responded to a handshake when last probed, and "auth required" means it demanded credentials. Both are statements about reachability, never about trustworthiness.

Other capabilities

Analytics and monitoring
1,099 verified tools
Files and storage
1,035 verified tools
Calendar and scheduling
723 verified tools
Crypto and blockchain
708 verified tools
Payments and billing
706 verified tools
Images, audio and video
637 verified tools
Maps, location and weather
598 verified tools
Web scraping and browser automation
490 verified tools
Social media
481 verified tools