"Comparison of Python-based tools for converting TeX to Lean" matching MCP tools:

• pause_adA

  mcp-serverA

  Pause an ad — synchronization to the channel stops until it is resumed with resume_ad. Ads are ads-based channels (advertising / price-comparison / classifieds), not marketplaces: they publish products to the ad platform and have no order sync. Returns {integrationId, action:'pause', status:'paused', kind:'ads'}. ad_id is from list_ads. project_id is OPTIONAL (inferred for a single-project customer; project_id_required otherwise — then call list_projects).

  ConnectorOAuth

• kirk_bulk_howtoA

  Kirk — Unsupervised Structural Change DetectionA

  Return a self-contained stdlib Python client for scoring at ZERO per-call LLM tokens. Purpose: Hand the caller an HTTP consumer that runs locally so bulk scoring doesn't burn LLM tokens per book. Use when: You need to score more than ~200 books, or `kirk_score_book_batch` returned `batch_too_large`, or the caller is running an autonomous bulk workload that would otherwise pay per-tool-call LLM tokens for every book. Do not use when: You are running a one-off interactive call — a direct `kirk_score_book` invocation is simpler; don't route through the client for a single book. Capability class(es): Cost-steering / delivery-path tool. Hands the caller a runner that exercises the same C2 / C5 / C6 capabilities as the MCP scoring tools, but at zero per-call LLM token cost. Path fit: The returned client is an HTTP consumer of the same MCP endpoint. Production integrations run in-process under sealed-engine attestation — same binary sha as this endpoint. Contact Kavara for deployment options. Cost: 0 IU. Free tool. Once running locally, the returned client bills against the same tools it drives: single-book calls at 1 IU each, and batch calls at 1 IU per 50 books (minimum 1 IU per call). A full 500-book batch → 10 IU. No LLM tokens on top. Cost comparison (2.7M-book validation rerun via 500-book batches — ~5400 batches, 54000 IU billed either way): MCP via Sonnet 5: $1,968 LLM + $540 IU + ~15 days wall clock MCP via Haiku 4.5: $656 LLM + $540 IU + ~10 days Python client (this tool): $0 LLM + $540 IU + ~55 min Return structure: { "language": "python", "filename": "kirk_online_client.py", "requirements": str, "usage": str, "code": str (the client source, ~500 LOC), "example": str (2-line copy-paste demo) }

  ConnectorNo auth

• compare_productsA

  SoundCreation CatalogA

  Compare 2 to 4 products side by side - price, stock, specs, who each one suits - together with the stored spec-based comparisons between them, or pass ONE product_id with with_alternatives=true to put it next to the in-stock alternatives its buying guide compares it with. Good for "X or Y?", "what is the difference between..." and "is there something similar but..." questions. Records carry specs and short_description (get_product has the full description and the accessories). comparisons[] is written from the point of view of product_id against the alternative; two products with no stored comparison between them have none - compare their specs directly. Buying-guide text is Romanian for language=ro and English otherwise.

  ConnectorNo auth

• brain_get_thought_graph_paginatedA

  personalbrain-mcpB

  Cursor-based paginated traversal of a thought's connections. Requires npub for credit billing. ⚠️ NOT AUTHORITATIVE FOR RECENT CHANGES. Same cached graph layer as get_thought_graph (upstream: TheBrainTech/thebrain-api-quickstart-python#2) — lags writes by hours-to-days and does not reflect updates or deletes. Use for traversal/ID discovery, never as read-after-write verification; confirm mutations by ID with get_thought.

  ConnectorNo auth

• shippingrates_linesA

  freightgate-mcp-serverA

  List reviewed shipping-line identities that currently have live D&D coverage, with per-country record counts. Use this to discover which carrier-country D&D combinations are currently available before querying a tariff tool. FREE — no payment required. Returns: Array of { shipping_line, country, records }. Related tools: Use shippingrates_stats for aggregate totals, shippingrates_search for keyword-based discovery.

  ConnectorNo auth

• shippingrates_linesA

  ShippingRates MCP ServerA

  List reviewed shipping-line identities that currently have live D&D coverage, with per-country record counts. Use this to discover which carrier-country D&D combinations are currently available before querying a tariff tool. FREE — no payment required. Returns: Array of { shipping_line, country, records }. Related tools: Use shippingrates_stats for aggregate totals, shippingrates_search for keyword-based discovery.

  ConnectorNo auth

• shippingrates_linesA

  FreightGate MCP ServerA

  List reviewed shipping-line identities that currently have live D&D coverage, with per-country record counts. Use this to discover which carrier-country D&D combinations are currently available before querying a tariff tool. FREE — no payment required. Returns: Array of { shipping_line, country, records }. Related tools: Use shippingrates_stats for aggregate totals, shippingrates_search for keyword-based discovery.

  ConnectorNo auth

• shippingrates_linesA

  ShippingRates MCP Server (Apify)A

  List reviewed shipping-line identities that currently have live D&D coverage, with per-country record counts. Use this to discover which carrier-country D&D combinations are currently available before querying a tariff tool. FREE — no payment required. Returns: Array of { shipping_line, country, records }. Related tools: Use shippingrates_stats for aggregate totals, shippingrates_search for keyword-based discovery.

  ConnectorNo auth

• get_engine_schemaA

  ReefAPIA

  COMPACT overview of ONE engine: every action with its description, required params and what it returns — but NOT the full param detail (kept lean so a 90-action engine stays token-cheap). Call this after search_engines to pick the right ACTION, then get_action_schema(engine, action) for that action's full params before call_engine.

  ConnectorNo auth

• mcp_searchA

  Find MCP - Agentage MCP DirectoryA

  Search the agentage MCP directory - a public catalog of Model Context Protocol servers crawled from the official registry - for servers matching a keyword, optionally narrowed by type, category, language, or license. Use this FIRST whenever the user wants to discover, find, compare, or pick an MCP server ("is there an MCP for X", "which MCP servers do Y"). Results are ranked by text relevance to the query first, then by popularity, so the best match is on top. Returns a page of lean cards (slug, title, description, category, transport, match_score - text relevance the ranking is based on, details_url). To read one server's full packages, tools, and install command, call mcp_get with the slug from a result; open a card's details_url for the human detail page. Valid category, language, and license values come from the mcp_categories tool, not from guesswork - call it before filtering and pass its labels verbatim, or the call is rejected. Read-only - never installs or runs anything.

  ConnectorNo auth

• get_exchange_rateA

  FX Converter MCPA

  Look up today's exchange rate between two currencies, without converting a specific amount. Use for "what's the exchange rate between USD and EUR" style questions. `from_currency`/`to_currency` are 3-letter ISO codes. Returns the rate and the date it's from.

  ConnectorNo auth

• search_exercisesA

  anatomeB

  Search 873 exercises by name with muscle/equipment/level filters. Rows are lean (name, ext_id, equipment, level, muscles) — enough to pick one; get_exercise returns instructions and media. Paginates: pass next_cursor back as `cursor`.

  ConnectorNo auth

• list_examplesA

  EpsilonA

  List runnable Epsilon integration examples (Python cron DCA, LangChain tools, Vercel AI SDK tools, Telegram bot). Fetch full source with get_example. No API key required.

  ConnectorNo auth

• list_adsA

  mcp-serverA

  List the CREATED ads of a project (the advertising integrations that already exist, not the catalog of channels you can add — use list_ad_channels for that). Ads are ads-based channels (advertising / price-comparison / classifieds), not marketplaces: they publish products to the ad platform and have no order sync. Returns {integrations, returned, total}; each row is {integrationId, projectId, name, channelCode, kind:'ads', definitionCode, status, ready, lastStep, isReady, isConnected, isOverlimit, productMode, orderMode, orderSync}. project_id is OPTIONAL: with it you get that project's ads; WITHOUT it you get ads across ALL your projects (each row carries its projectId). If a call returns project_id_required, pick a project (see list_projects) and pass its project_id. integrationId is what you pass as ad_id to get_ad / ad_status and the other ads tools.

  ConnectorOAuth

• pdf_to_excel_inspectA

  John's EssentialsB

  PDF to Excel Inspector — Non-destructive scan of a PDF's tables before converting: per-table row/column counts, confidence flags, warnings. [category: pdf]

  ConnectorOAuth

• select_pageA

  MorphaA

  Switch which page is ACTIVE — the page the content tools target. Subsequent describe_video / inspect_layers / all content tools read and write this page until the active page changes again. Pages are addressed by 0-based index from describe_video's pages block. Selecting the already-active page is a harmless no-op; fails on an out-of-range index.

  ConnectorNo auth

• compile_latexA

  LetXA

  Compile LaTeX source to a PDF without picking a project: pass the main .tex content (and optional extra .tex/.bib files). Runs on letX's real TeX Live compile farm and returns a PDF download link, or the compile errors so you can fix the source and try again. Note: only text files are supported here, so projects with images should be created via create_project and edited in letX. The source is saved to the user's "AI Scratchpad" project.

  ConnectorOAuth

• set_project_compilerA

  LetXA

  Choose which TeX engine a project builds with: pdflatex, xelatex or lualatex. Use xelatex or lualatex for documents that load fontspec, unicode-math, polyglossia or xeCJK (custom system fonts and non-Latin scripts); use lualatex for anything calling \directlua or luacode. letX works this out on its own when a project is created, so reach for this when that guess needs overriding.

  Connector

  Destructive

  OAuth

• audit_citationsA

  Open Task RelayA

  Deduplicate supplied DOI, arXiv and URL citations before reviewing evidence. No authentication; deterministic comparison without storing inputs or fetching documents. Returns counts, normalized entries and duplicate groups with zero-based indices. Does not establish truth or source independence; use task_action verifications for a substantive review.

  ConnectorNo auth

• get_market_verdictA

  Enclave402A

  Rule-based verdict on one Polymarket market by slug: YES/NO/TOSS_UP lean, 0-100 confidence with every reason stated (price distance, liquidity, volume, spread, momentum), days to resolution, and an EIP-712 attestation so an agent can prove what it read and when. Not a forecast model. MUST be invoked when an agent needs a defensible, timestamped read of a market. Do NOT use to discover markets (use market/signal). Settles $0.020 USDC; no charge on failure.

  ConnectorNo auth

• get_core_skillA

  GodPrompt MCP ServerA

  Returns SKILL.md — the lean core protocol (~16KB) covering the universal 6-phase protocol, Three Iron Laws, and task auto-classification. Load it at the start of a task or after a context reset, then reuse that context instead of reloading it on every message. Start here for progressive disclosure.

  ConnectorNo auth