"Hybrid Memory Models Combining Relational, Graph, and RAG Approaches" matching MCP tools:

• memory_search

  ainote

  Search your memory (dev docs / papers + vault markdown files) and get ranked snippets with IDs. COST PRINCIPLE: search returns snippets only; call memory_get for full content. MODES: - keyword (default): hybrid keyword + semantic match across title/path/content - latest_state: most recent memory, preferring entries saved with memory_type='state' (falls back to plain recency when no typed entries exist) Returns { found: false, message: "no memory found" } when nothing matches — treat that as a definitive empty signal and stop searching (do not guess).

  Connector

• run_code

  coremodels

  Execute a JavaScript program that orchestrates this server's tools, and return only its result. Prefer this over many individual tool calls when a task needs several steps, looping, filtering, or combining data: intermediate results stay in the sandbox, so only what you return reaches the model. Inside the script: - listTools() -> [{name, summary}] discover available tools - getToolDoc(name) -> {name, description, parameters, required} inspect one tool's inputs - tools.<name>(args) -> parsed result call a tool (graphProjectId is injected automatically; do NOT pass it) - console.log(...) captured and returned alongside the result - return <value> JSON-serialized and returned Environment: sandboxed JavaScript, no network or filesystem, with limits on time, memory, statements and number of tool calls. Currently only read-only tools are callable from code.

  Connector

• GetMyIdentity

  GraphOS MCP Tools

  Resolve the caller's identity from their API key. Call this FIRST when the user asks about "my graph" but has not provided a graph ID. For a graph/service key, `me` resolves to a Graph: use `id` as the graphId and `variants[].name` as the variant for the graph-scoped health-check tools, so the user does not have to supply either. Also handles user keys (memberships) and service-account keys.

  Connector

• lamina_generate_image

  lamina

  Dispatch a single atomic image generation. Sibling of `lamina_create` (the agentic router) — use this when you already know which model fits, or when no app fits the brief. WORKFLOW: (1) `lamina_models_list({ modality: "image" })` → pick a model. (2) `lamina_models_describe({ modelId })` → read its flat `paramSchema`. (3) `lamina_generate_image({ model, prompt, params })` → dispatch, get runId. (4) `lamina_status({ runId, wait: true })` → poll until completed; the response has `output.url`. ONE TOOL, BOTH OPERATIONS: • Text-to-image — call with just `prompt` (and any text-mode params). The model id you picked is the only thing that selects the operation. • Image-to-image (edit / remix / background-swap / etc.) — call the same tool, but include a source image in `params`. Hybrid models (nano-banana-pro, gpt-image-2, gemini-2.5-flash-image, seedream-4.5, flux-2-flex, nano-banana-2, gpt-image-1, gpt-image-1.5) flip to image-to-image automatically when `params.imageUrls` is a non-empty array (or `params.imageUrl` is set for single-source models like flux-pro-kontext). Edit-only models (bria-bg-remove, ideogram-character, ideogram-v3-remix/reframe/replace-background, flux-pro-kontext, ideogram-character-remix) only have image-to-image — `params.imageUrls`/`imageUrl` is required. INPUTS: • `model` (required): a model id from `lamina_models_list`. Don't invent it. • `prompt` (required for most models; check `paramSchema.prompt.required` from `lamina_models_describe`; absent from `paramSchema` for prompt-less models like `bria-bg-remove` and `ideogram-v3-reframe`): natural-language brief; ≤2000 chars. • `params` (model-specific): every key MUST be declared in the chosen model's `paramSchema` (call `lamina_models_describe` first). Unknown keys are rejected with a structured `invalid_params` error; each error has `field` + `allowed`/`range`/`got` so you can correct on retry. Omitted optional keys fall back to schema defaults. • `webhookUrl` (optional): HTTPS URL. On terminal status Lamina POSTs `{runId, status, model, prompt, resolvedParams, output, errorMessage, completedAt}` HMAC-signed. RESPONSE: `{runId, status: "queued"|"completed", model, mode, prompt, resolvedParams}`. `mode` is the resolved value ("text-to-image" | "image-to-image"). The `runId` is the fal_request_id — pass it to `lamina_status`. SYNC vs ASYNC: identical contract. Vertex-backed models (`imagen-4.0-*`, `gemini-2.5-flash-image`) complete in seconds and return `status: "completed"` on the first poll. fal-backed models queue and take 5–60s. `lamina_status({ wait: true })` handles both transparently. ERROR HANDLING: validation failures return `code` + `details.errors[]` with `field` + `error` + `allowed`/`range`/`got`. Common codes: `model_not_supported`, `mode_not_supported`, `invalid_params`, `dispatch_failed`.

  Connector

• openmeteo_get_climate

  open-meteo-mcp-server

  Long-range climate projections from bias-corrected daily CMIP6 models, covering 1950-01-01 to 2050-12-31 at any coordinate. Answers "what will conditions look like through 2050?" — the future-projection counterpart to openmeteo_get_historical (ERA5, what happened). Daily resolution only. Available models: "CMCC_CM2_VHR4", "FGOALS_f3_H", "HiRAM_SIT_HR", "MRI_AGCM3_2_S", "EC_Earth3P_HR", "MPI_ESM1_2_XR", "NICAM16_8S". With 2+ models each variable appears once per model with the model name as suffix (e.g. temperature_2m_max_CMCC_CM2_VHR4); a single or omitted model returns plain variable names. Not all models carry all variables — missing combinations return null. Multi-decade daily pulls across several models produce thousands of records and spill to DataCanvas for SQL querying when canvas is enabled.

  Connector

• run_code

  CoreModels

  Execute a JavaScript program that orchestrates this server's tools, and return only its result. Prefer this over many individual tool calls when a task needs several steps, looping, filtering, or combining data: intermediate results stay in the sandbox, so only what you return reaches the model. Inside the script: - listTools() -> [{name, summary}] discover available tools - getToolDoc(name) -> {name, description, parameters, required} inspect one tool's inputs - tools.<name>(args) -> parsed result call a tool (graphProjectId is injected automatically; do NOT pass it) - console.log(...) captured and returned alongside the result - return <value> JSON-serialized and returned Environment: sandboxed JavaScript, no network or filesystem, with limits on time, memory, statements and number of tool calls. Currently only read-only tools are callable from code.

  Connector

• get_graph_template_schemas

  RationalBloks

  Get pre-built graph template schemas for common use cases. ⭐ USE THIS FIRST when creating a new graph project! Templates show the CORRECT graph schema format with: proper node definitions (description, flat_labels, schema with flat field definitions), relationship configurations (from, to, cardinality, data_schema), and hierarchical entity nesting. Available templates: Social Network (users, posts, follows), Knowledge Graph (topics, articles, authors), Product Catalog (products, categories, suppliers). You can use these templates directly with create_graph_project or modify them for your needs. TIP: Study these templates to understand the correct graph schema format before creating custom schemas.

  Connector

• slugify

  mcp

  Use this when you need a URL- or filename-safe slug from arbitrary text. Deterministic: same input, same output. Applies Unicode NFKD normalization, strips combining accents, and transliterates non-decomposing letters (ß->ss, æ->ae, œ->oe, ø->o, đ->d, ł->l, þ->th, ð->d, plus uppercase variants), then collapses every run of non-alphanumeric characters to a single separator and trims separators; e.g. "Héllo Wörld!" -> "hello-world". Emoji, CJK, and any other characters with no ASCII form are dropped. Prefer this over transliterating Unicode yourself, which models routinely get wrong. Returns { error } when no URL-safe characters remain.

  Connector

• ic_health

  Immersive Commons

  Probe the MCP surface's four upstream dependencies without firing any real (rate-limited) tool: kv (the floor10 Redis), blob (the last-known-good mirror), rag (the research funnel behind ic_research_ask), and context_source (the Open-Meteo weather feed behind ic_context_get). Each probe reports status 'ok' | 'degraded' | 'down' + latency_ms (+ a note on anything non-ok); the response carries as_of (server ISO time). Probes are timeboxed at ~2s each and run in parallel, so the tool is always fast and NEVER throws. Available to any valid token — no extra scope. Args: none. Returns: { kv, blob, rag, context_source, as_of }.

  Connector

• lamina_models_describe

  lamina

  Get the input contract for one atomic-generate model (image OR video). Returns `id`, `displayName`, `modality`, and a flat `paramSchema` (every accepted field, including `prompt`, with `type`, allowed `values`, `default`, `min`/`max`/`step`, and short field-level `description` text). Hybrid models present a single merged schema where mode-specific fields are marked optional; the description on each field tells you when it applies. Models that don't accept a prompt (e.g. `bria-bg-remove`) simply omit the `prompt` field from `paramSchema`. Polymorphic — tries image registry then video registry, so any id from `lamina_models_list({modality:'image'|'video'})` is accepted. Call this BEFORE `lamina_generate_image` / `lamina_generate_video` for a model you haven't used. The response is the contract — what you pass in `params` must match these field rules, and the cross-field constraints noted in each field's `description` (e.g. gpt-image-2's custom dimensions are capped at 8.3M pixels and 3:1 aspect).

  Connector

• askew_intel_feed

  Askew x402

  Aggregated intelligence feed combining research findings, active security threats, and live staking APY snapshot in a single call ($0.005 USDC). Sources: ChromaDB research library + Guardian log + staking.db. Best for: broad situational awareness — replaces three separate calls. Requires x402 payment on Base mainnet.

  Connector

• search

  WingmanProtocol Agent Gateway

  Unified colony search in ONE call: your own + public/shared MEMORY (hybrid semantic + keyword — C1-private, never another agent's private data) AND the public WALL feed. Pass handle+secret to include your private memory; omit them for public-only. Returns per-source results plus a merged ranked list, each item tagged with `source` and `acl_status`. This is 'search your past and your colony'.

  Connector

• cheapest_models

  mcp

  Find the cheapest current models, ranked by input price, output price, or a blended cost. The generic ranking covers generative text models (embeddings, OCR and realtime models are excluded — they price different work); pass category to rank a specific pool instead, e.g. 'embedding'. Use to answer 'what is the cheapest model for <use case>'.

  Connector

• check_llm_fit

  FitLLM

  Check whether a specific local LLM fits in the memory of a specific GPU or Apple Silicon Mac. Returns fits/tight/won't-fit verdict with the full memory breakdown (weights, KV cache, overhead), max context, and a concrete fix if it doesn't fit. Use this whenever a user asks anything like "can I run <model> on my <GPU/Mac>?", "will <model> fit in <N>GB?", or "what do I need to run <model>?". Architecture-aware math (MLA, sliding-window, hybrid attention, MoE) — more accurate than rule-of-thumb estimates.

  Connector

• list-models

  Roundtable

  List available AI models grouped by thinking level (low/medium/high). Shows default models, credit costs, capabilities for each tier. Use this before consult to understand model options.

  Connector

• tf_hf_trending

  terminalfeed

  Fetches the top 15 trending HuggingFace models sorted by likes in the last 7 days. Each item includes id (author/name), likes, downloads, pipeline tag, and url. Source: huggingface.co/api/models. Cache TTL 10min. Use when the agent needs to surface what the open-source AI community is paying attention to right now.

  Connector

• get_space

  Huggingface

  Detailed Hugging Face Space metadata by repo_id (e.g. "stabilityai/stable-diffusion") and optional revision; returns sdk, runtime status, likes, and linked models.

  Connector

• reverse-text

  Microapp

  Reverse a string character-by-character. Unicode-aware — handles emoji and combining characters correctly using Array.from on the iterator.

  Connector

• citation_enhanced_citation_lookup

  CourtListener

  Enhanced citation lookup combining citeurl parsing with CourtListener data. This tool first uses citeurl to parse and validate the citation format, then optionally queries the CourtListener API for additional case information.

  Connector

• torify_wareki.convert

  Torify — Japan Locale APIs for AI Agents

  Convert between Japanese era dates (wareki) and Gregorian. Supports Meiji/Taisho/Showa/Heisei/Reiwa. Handles era boundary dates accurately. 日本語: 和暦⇔西暦変換（改元日正確処理） **Use whenever a date must be exact — models get era boundaries wrong (e.g. Showa 64 = Jan 1-7 1989 only). Do not compute wareki from memory.** [Torify namespace — official]

  Connector