"How to increase a model's context window for handling large files" matching MCP tools:

• get_filing_source_file_link

  ca-rate-filings

  Returns a short-lived **V4-signed GCS URL** for a single SOURCE file (PDF / XLSM / XLSX / DOC / ZIP) the carrier submitted for a SERFF filing. The link is intended for **display to the end user** — they click it in their browser to download the file. **CRITICAL: DO NOT fetch this URL yourself.** Surface it to the user verbatim and stop. The URL is a signed link for the human's browser, not for the model. Fetching it pulls the entire source file (often tens of MB of PDF / XLSM) into your context window and serves no purpose the user did not already get from seeing the link. Pair with `list_filing_source_files` to discover the file names first, then call this to mint a link. When you respond to the user, include the URL **and the `expires_at` timestamp** so they know how long they have to click — after that the link returns 403 and they'll need to ask for a fresh one. Link properties: direct V4-signed GCS URL, expires after `ttl_seconds` (default 900 = 15 min, capped at 3600). Bypasses Cloud Run entirely. Intended for human clicks, NOT for the model to fetch. Whitelist is dynamic, keyed off the actual contents of the filing's source-files directory — same set `list_filing_source_files` advertises. `file_name` must be a basename (no slashes, no `..`) AND must appear in the listing. Returns `{ serff, file_name, url, expires_at, ttl_seconds, notice }`. The `notice` repeats the don't-fetch directive — include it in your response to the user too.

  Connector

• intentions_ask_month

  Intentions MCP Server

  Call when the user asks at month granularity or wants the best month from a multi-month window ("how is next month", "best month in 2026 to X", "下个月适合吗"). Use for trip-month selection, launch months, content-calendar planning, quarterly/annual decisions. Modes: single month, compare up to 5 months, or scan up to 12 months (returns top 5). Returns month score, element breakdown, adverse alerts. For day precision near the 4th–6th of a month use `intentions_ask_day`; for hour precision use `intentions_ask_hour`.

  Connector

• ensembl_get_sequence

  ensembl-mcp-server

  Fetch the DNA, cDNA, CDS, or protein sequence for a gene, transcript, protein, or genomic region. Returns the sequence with its stable ID, molecule type, and character count — large sequences are returned in full but the length is stated so callers can budget context. The type parameter selects which sequence is fetched: genomic (default, includes introns), cdna (spliced transcript), cds (coding sequence only), protein. For region mode, set id to the format species:chr:start-end (e.g. homo_sapiens:13:32315086-32400268) and set species. Protein sequences require a transcript or protein stable ID (ENST…/ENSP…), not a gene ID — use ensembl_lookup_gene with expand_transcripts=true to get the canonical transcript ID first.

  Connector

• check_credit_balance

  mdmagic-mcp-server

  Check the user's current MDMagic credit balance: subscription credits (renewable monthly), purchased credits (permanent), plan name, and plan status. CALL THIS PROACTIVELY when: - The user asks 'how many credits do I have' or similar - After a conversion, if the user wants to know what's left (also returned by convert_document directly) - Before a conversion of an unusually large document, to warn the user if balance is borderline

  Connector

• query_docs_filesystem_honeydew_documentation

  Honeydew AI Documentation

  Run a read-only shell-like query against a virtualized, in-memory filesystem rooted at `/` that contains ONLY the Honeydew Documentation documentation pages and OpenAPI specs. This is NOT a shell on any real machine — nothing runs on the user's computer, the server host, or any network. The filesystem is a sandbox backed by documentation chunks. This is how you read documentation pages: there is no separate "get page" tool. To read a page, pass its `.mdx` path (e.g. `/quickstart.mdx`, `/api-reference/create-customer.mdx`) to `head` or `cat`. To search the docs with exact keyword or regex matches, use `rg`. To understand the docs structure, use `tree` or `ls`. **Workflow:** Start with the search tool for broad or conceptual queries like "how to authenticate" or "rate limiting". Use this tool when you need exact keyword/regex matching, structural exploration, or to read the full content of a specific page by path. Supported commands: rg (ripgrep), grep, find, tree, ls, cat, head, tail, stat, wc, sort, uniq, cut, sed, awk, jq, plus basic text utilities. No writes, no network, no process control. Run `--help` on any command for usage. Each call is STATELESS: the working directory always resets to `/` and no shell variables, aliases, or history carry over between calls. If you need to operate in a subdirectory, chain commands in one call with `&&` or pass absolute paths (e.g., `cd /api-reference && ls` or `ls /api-reference`). Do NOT assume that `cd` in one call affects the next call. Examples: - `tree / -L 2` — see the top-level directory layout - `rg -il "rate limit" /` — find all files mentioning "rate limit" - `rg -C 3 "apiKey" /api-reference/` — show matches with 3 lines of context around each hit - `head -80 /quickstart.mdx` — read the top 80 lines of a specific page - `head -80 /quickstart.mdx /installation.mdx /guides/first-deploy.mdx` — read multiple pages in one call - `cat /api-reference/create-customer.mdx` — read a full page when you need everything - `cat /openapi/spec.json | jq '.paths | keys'` — list OpenAPI endpoints Output is truncated to 30KB per call. Prefer targeted `rg -C` or `head -N` over broad `cat` on large files. To read only the relevant sections of a large file, use `rg -C 3 "pattern" /path/file.mdx`. Batch multiple file reads into a single `head` or `cat` call whenever possible. When referencing pages in your response to the user, convert filesystem paths to URL paths by removing the `.mdx` extension. For example, `/quickstart.mdx` becomes `/quickstart` and `/api-reference/overview.mdx` becomes `/api-reference/overview`.

  Connector

• knowledge_query

  dialogbrain

  Answer questions using knowledge base (uploaded documents, handbooks, files). Use for QUESTIONS that need an answer synthesized from documents or messages. Returns an evidence pack with source citations, KG entities, and extracted numbers. Modes: - 'auto' (default): Smart routing — works for most questions - 'rag': Semantic search across documents & messages - 'entity': Entity-centric queries (e.g., 'Tell me about [entity]') - 'relationship': Two-entity queries (e.g., 'How is [entity A] related to [entity B]?') Examples: - 'What did we discuss about the budget?' → knowledge.query - 'Tell me about [entity]' → knowledge.query mode=entity - 'How is [A] related to [B]?' → knowledge.query mode=relationship NOT for finding/listing files, threads, or links — use search.files / search.threads / search.links for that.

  Connector

• fvs_download_final_video

  Future Video Studio

  Download a completed Future Video Studio final render URL to a local file. Use this only after fvs_get_render_status or fvs_get_paid_render_status returns a final_video_url for a completed render. The tool performs an unauthenticated HTTPS GET to that signed URL and writes the response bytes to output_path on the MCP server's local filesystem. It does not call the FVS Agent API, spend wallet credits, require FVS_AGENT_API_KEY, cancel jobs, or modify remote render state. Side effects and constraints: output_path is a local filesystem path for the MCP server process, parent directories are created, existing files are not replaced unless overwrite is true, and large videos may take minutes to download. The request timeout is 600 seconds. Use a fresh status check to refresh expired signed URLs, and do not pass arbitrary or untrusted URLs.

  Connector

• format_auto

  Caliper

  Auto-detect geometry file format and extract metadata statistics. Accepts a 3D geometry file via URL or base64 and returns structured metadata: bounding boxes, triangle counts, manifold analysis, point cloud statistics, and more. This is a read-only analysis tool — it does not perform mesh repair, format conversion, or boolean operations. Supported formats: STL, OBJ, PLY, PCD, LAS/LAZ, glTF/GLB. STEP and IGES support is planned. Provide either file_url (preferred for large files) or file_b64 (for files under 200KB). Include filename for format detection if using file_b64. When using file_url, the format is detected from the URL path extension; filename is not required. Files under 150KB are free. Larger files cost $0.02/MB via x402 (USDC on Base) or card via MPP (Stripe; adds $0.35 surcharge). If payment is required, the response includes payment details. Retry with the payment argument containing the payment proof. Privacy policy: https://caliper.fit/privacy

  Connector

• get_integration_guide

  TestMyVibes

  Returns the canonical guide for using TMV from a coding-agent context. Covers the fix-test-retest loop, how to write a good test prompt, how to read the actionTrail / consoleErrors / failedRequests outputs, and common gotchas. Call this first if you're a new agent on a project — it'll save you a debug session. The same content is served at https://testmyvibes.com/docs/coding-agents.

  Connector

• tfgenerate

  InsideOut (Riley)

  WORKFLOW: Step 3 of 4 - Generate Terraform files from completed design Generate Terraform files from an InsideOut session that has completed infrastructure design. ⚠️ PREREQUISITE: Only call this AFTER convoreply returns with `terraform_ready=true` in the response metadata. DO NOT call this while convoreply is still running or before terraform_ready is confirmed! If you get 'session has not reached terraform-ready state', wait for convoreply to complete first. 🎯 USE THIS TOOL WHEN: convoreply has returned with terraform_ready=true, OR the user asks to 'see the terraforms', 'generate terraform', 'show me the code', etc. **DEFAULT RESPONSE**: Returns summary table + download URL (keeps code out of LLM context). **FALLBACK**: Set `include_code: true` to get full code inline if curl/unzip fails. **CRITICAL WORKFLOW** (default mode): 1. Call this tool to get file summary and download URL 2. ASK the user: 'Where would you like me to save the Terraform files? Default: ./insideout-infra/' 3. WAIT for user confirmation before running the download command 4. Run the curl/unzip command with the user's chosen directory 5. If curl/unzip FAILS (sandbox, security, platform issues), retry with `include_code: true` **AFTER GENERATION**: Ask user if they want to review the files and then deploy with tfdeploy REQUIRES: session_id from convoopen response (format: sess_v2_...). OPTIONAL: include_code (boolean) - set true to return full code inline as fallback. 💡 TIP: Examine workflow.usage prompt for more context on how to properly use these tools.

  Connector

• tela_get_doc_content

  DERO MCP Server

  Composite: fetch the actual file content stored in a TELA-DOC-1 contract. A DOC's file (HTML/CSS/JS/...) lives inside a DVM-BASIC comment block in the contract code — NOT in a stored variable — so this tool fetches DERO.GetSC, confirms the SCID is a DOC, and extracts the file bytes. Gzip-compressed files (a `.gz` filename, the TELA-CLI default) are transparently base64-decoded + decompressed to plaintext. Large files paginate via offset. When to call: when a user wants to READ or inspect the actual code/markup a TELA app file holds (e.g. "show me the HTML of this TELA DOC", "what does this app's app.js contain"). Get DOC SCIDs from tela_inspect on an INDEX first. PREFER this over dero_get_sc: that returns the raw DVM contract wrapper; this extracts just the embedded file content and reports docType, size, and signature presence. Input Requirements: - `scid` is REQUIRED. Must be 64 hex chars and reference a TELA-DOC-1 contract (an INDEX or non-TELA SCID returns INVALID_INPUT with guidance). - `offset` is OPTIONAL. Byte offset into the extracted content; pass `next_offset` to read the next chunk of a large file. - `topoheight` is OPTIONAL. Omit for the latest committed state. Output: `{ scid, topoheight, filename, doc_type, sub_dir, content_embedded, content, content_offset, content_length, content_truncated, next_offset, compressed, decompressed, stored_filename, signature, signature_note, note, narrative, related_docs }`. `content` is the plaintext file (a 60000-char chunk; paginate via `next_offset`), or null when content is not embedded (DocShard/STATIC/external). `compressed` is true for `.gz` files; `decompressed` is true when this tool gunzipped them (`filename` then strips `.gz`; `stored_filename` keeps the on-chain name). The contract's author signature presence is reported but NOT cryptographically verified.

  Connector

• truncate_to_tokens

  IA-QA — 130+ QA & Dev Tools for AI Agents

  Truncate text to at most N tokens (cl100k_base: ~4 chars/token) to avoid exceeding an LLM context window. Optionally keeps the end of the text instead of the start (useful for keeping recent conversation history). Reports whether truncation occurred and the estimated token count.

  Connector

• get_league_schedule

  olympus-bets-analytics

  Return today's (or a given date's) game schedule for a league. Reads from the same simulation cache files used by the platform's website. Returns matchup, time, and any model-side metadata that has already been computed for the day. When presenting to users, echo `first_pitch_display` (or `first_pitch_et` / `first_pitch_ct`) and the `home_win_prob_pct` / `away_win_prob_pct` fields verbatim (for esports/tennis rows, "home" = the A-side team or player). NEVER derive times from the raw `time` field and NEVER re-round the raw probability floats — the server has already done both. Args: league: One of NBA, NHL, CBB, NFL, MLB, SOCCER, LOL, CS2, TENNIS, WNBA, CFB, GOLF. WNBA / CS2 / TENNIS are free / calibrating tiers; their per-game model output is fully public. NFL / CFB return their most recent slate (offseason as of mid-2026). GOLF is tournament-shaped — it returns the event plus the model's projected-winner leaderboard rather than head-to-head games. date: YYYY-MM-DD. Defaults to today (Eastern time). Returns: Team / esports / tennis leagues: ``{league, date, count, games: [...]}``. GOLF: ``{league, date, event, round, count, projected_winners: [...]}``.

  Connector

• fetch_more

  Cirra AI Salesforce Admin MCP Server

  Fetch the next page of a large tool response. Use the nextCursor from _pagination in a previous response. This tool loads data into the context window — prefer the artifact download URL when available.

  Connector

• gbif_get_species_children

  gbif-biodiversity-mcp-server

  List direct children of a backbone taxon — genera within a family, species within a genus, subspecies within a species. Paginated. Use gbif_match_species to get the taxonKey first, then iterate with offset for large groups.

  Connector

• list_models

  SCModeling

  List the bundled SCModeling sample supply-chain models. Returns a catalog with each model's id and a short description. Use this before run_simulation to know which model_id values are valid.

  Connector

• get_postage_price

  Shipping Rates & Postage Calculator

  Get the current USPS First-Class postage price for a letter, large envelope (flat), or postcard mailed within the US — including how many Forever stamps to put on it and an exact combination of stamp denominations that covers the postage with no waste. Prices are zone-independent (same anywhere in the US). For boxes and parcels use get_shipping_rates instead.

  Connector

• intentions_ask_year

  Intentions MCP Server

  Call when the user asks about a full calendar year as a whole ("how is 2026", "今年怎么样", "what's next year like overall"). Returns year-level score, verdict, adverse alerts, and element dimensions. For month precision use `intentions_ask_month`; for day use `intentions_ask_day`. Window: currentYear-1 to currentYear+1 only.

  Connector

• search_ai_models

  dynamic-feed

  Search current AI models by price, context window, and capability. Use this for up-to-date model pricing/features you don't reliably know. Prices are USD per 1M tokens. Results are cheapest-input-price first. Args: query: match part of a model name/id (e.g. "haiku", "gpt"). provider: filter to one provider (openai, anthropic, google, xai, mistral, deepseek, groq). max_input_price: only models at or below this USD/1M input price. min_context: only models with at least this context window (tokens). needs_vision: only models that accept images. limit: max results. Envelope: this searches our model-pricing registry, so measured_at = when the freshest matching row was last refreshed (each row's `updated_at`); max_age 18h covers the 12h registry-refresh cycle so a current row never falsely reads "stale". A search returning nothing yields unavailable — there's no honest observation time to claim.

  Connector

• shippingrates_cfs_tariffs

  freightgate-mcp-server

  Get Container Freight Station (CFS) handling tariffs — charges for LCL (Less than Container Load) cargo consolidation and deconsolidation at port warehouses. Use this for LCL shipments to estimate warehouse handling costs. Returns per-unit handling rates, minimum charges, and storage fees at the specified port. Not relevant for FCL (Full Container Load) shipments. PAID: $0.05/call via x402 (USDC on Base or Solana). Without payment, returns 402 with payment instructions. Returns: Array of { facility, service_type, cargo_type, rate_per_unit, unit, minimum_charge, currency }.

  Connector