"Iterative Code Development and Analysis Guidelines" matching MCP tools:

• list_skills

  civilquants

  List the 10 senior-QS skill methodologies CivilQuants exposes (tender review, risk assessment, QS measurement/contract advice, geotechnical + geo-environmental interpretation, earthworks, preliminaries, pavement design, subcontract analysis). Universal discovery — both tiers see the full list. Returns each skill's slug, title, one-line summary and tier; then call get_skill(skill=<slug>) to fetch the methodology body. The skills are paid-tier; a free caller gets a sign-up prompt from get_skill. NOTE: the document-heavy skills (tender review, the interpretation skills) need a code-execution client (Claude Code / Codex / VS Code) plus the chunking pack from get_document_pipeline to run a real tender pack — on a chat connector you can read the methodology but cannot chunk/parse files.

  Connector

• execute_code

  L&T MCP

  IMPORTANT: You MUST call this tool to generate any file. Do NOT write code as text. Do NOT tell the user to run code themselves. ALWAYS pass the code to THIS tool and return the download_url to the user. Execute Python code in an isolated Jupyter kernel and return output text + any generated files as base64 and download URLs. YOU MUST USE THIS TOOL when user asks for: - PPT / presentation / slides / deck → use python-pptx, call this tool - PDF / document / report → use reportlab, call this tool - Chart / graph / plot / visualization → use matplotlib, call this tool - Excel / spreadsheet → use openpyxl, call this tool - Word document → use python-docx, call this tool - ANY file generation task → call this tool WORKFLOW — follow exactly: 1. Write the complete Python code 2. Call THIS tool with that code 3. Get back download_url from the result files list 4. Show download_url to user as a clickable link NEVER skip step 2. NEVER output code as text to the user. Pre-installed packages (no pip install needed): python-pptx → PowerPoint presentations reportlab → PDF creation matplotlib → charts and graphs pandas → data analysis numpy → numerical computing python-docx → Word documents openpyxl → Excel files plotly → interactive charts seaborn → statistical charts Pillow → image processing pypdf → read/merge/split PDFs pdfplumber → extract text and tables from PDFs File saving rules — MUST follow: Save ALL files to current directory — NO path prefix prs.save("presentation.pptx") ← PowerPoint plt.savefig("chart.png", dpi=150) ← matplotlib chart df.to_excel("report.xlsx") ← Excel Always print() the filename after saving

  Connector

• get_ai_development_loop_info

  Fractera

  Explains the Fractera development loop: how one admin request becomes tested, deployed, recorded code with no human writing it — Hermes orchestrates and loads its identity + project context, picks a ready coding agent (Claude Code, Codex, Gemini, Qwen, Kimi), the agent is enriched (SOUL.md / AGENTS.md / GLOSSARY.md / completed steps), generates a task then code, it is built and deployed, and the result branches (error feeds back; success updates the completed steps and the deployments tab) — all grounded by LightRAG memory at every step. RETURNS A DIAGRAM IMAGE URL you can show the user when they ask how Fractera builds software or how its agents work. Call with NO arguments to get the diagram URL + the "how the loop works" overview + the section list; call again with a single `section` id to read one stage in depth.

  Connector

• change_startup_stage

  BetaFinds

  Change your startup's product stage: PRELAUNCH — preparing to launch, BETA — recruiting beta testers, PAUSED — development paused (requires public_note). To move to LAUNCHED use announce_launch. Allowed transitions: PRELAUNCH→BETA/PAUSED, BETA→PAUSED, PAUSED→PRELAUNCH/BETA.

  Connector

• post_lint_php

  webbersites-x402-data-api

  PHP lint: POST {code}, get the bugs back with line numbers. Deterministic static analysis — code is never executed, no AI. Catches SQL injection (request data interpolated into query strings), the removed mysql_* API, unbalanced braces, '+' string concat, = vs == in conditions, type-juggling loose comparisons, eval/extract on request data, unused variables, leftover var_dump. Understands PHP tags, heredocs, interpolation. Max 128 KB. ($0.002 per call, paid via x402)

  Connector

• get_boundary_by_code

  Boundr

  Look up metadata for a single UK boundary by its ONS census code. No geometry. Use this when you already have a census code (e.g. from search_boundaries_by_name() or find_boundaries_at_point()) and need structured metadata such as area size or type label. If you also need the boundary shape for display or analysis, call get_boundary_geojson_by_code() instead. ONS census codes (sometimes called GSS codes or LAU codes) are stable identifiers of the form "E09000012" (Hackney), "E10000016" (Kent), etc. The first letter indicates the country: E = England, W = Wales, S = Scotland, N = Northern Ireland.

  Connector

• get_boundary_geojson_by_code

  Boundr

  Fetch the full GeoJSON geometry for a UK boundary by its ONS census code. Returns a GeoJSON Feature object (WGS-84 / EPSG:4326) suitable for rendering on a map or performing geometric analysis. The geometry can be large — county and ceremonial county polygons are especially heavy. Only call this when you specifically need the shape; for metadata only use get_boundary_by_code() instead. IMPORTANT — Leaflet / web maps: use get_boundary_geojson_simplified() instead. The full geometry is large enough to exhaust your context window before you can finish writing the page. The simplified version is safe to embed directly in HTML and indistinguishable from the full shape at normal map zoom levels. Use this tool only when you need full-fidelity geometry for server-side analysis (e.g. precise point-in-polygon checks, area calculations, clipping). Obtain the census code from search_boundaries_by_name() or find_boundaries_at_point() before calling this.

  Connector

• cc.squirrel_chat_v2

  Central Command

  Call cc.squirrel_chat_v2 — Full AI trading assistant powered by GPT that can analyze markets, compute indicators, fetch live data, place orders, manage positions, and provide strategic advice. Purpose: Full AI trading assistant powered by GPT that can analyze markets, compute indicators, fetch live data, place orders, manage positions, and provide strategic advice. Behavior: conversational AI that CAN place/cancel orders and manage positions when the linked account allows it. Treat as potentially destructive. Confirm intent before asking it to trade live. Auth: X-Api-Key required (and linked exchange credentials for execution actions). Cost: $0.03 USDC per successful call (x402 Base USDC pay-per-use or prepaid X-Api-Key balance). Linked Connect keys are free. This is billing, not a side effect. Rate limit: 10/min (per API key). Tier: enterprise. Returns: Conversational AI response with embedded trade execution, market analysis, indicator computations, and chart drawing commands. Guidelines: Prefer paper/simulation paths. For live money require explicit human confirmation (confirm_live / action=execute). Report real HTTP errors; never invent proxy failures. Tags: ai, agent, autonomous, trading, analysis, execution, conversational.

  Connector

• cc.strategy_backtest

  Central Command

  Call cc.strategy_backtest — Takes a natural language strategy description, generates executable code, and runs it against historical OHLCV data with full TP/SL/trailing stop simulation. Purpose: Takes a natural language strategy description, generates executable code, and runs it against historical OHLCV data with full TP/SL/trailing stop simulation. Behavior: READ-ONLY. Does not place orders, move funds, or mutate your exchange account. Live / near-real-time data. Auth: X-Api-Key or x402 payment proof (X-PAYMENT / __x_payment). Anonymous unauthenticated calls receive HTTP 402 with payment accepts. Cost: $0.05 USDC per successful call (x402 Base USDC pay-per-use or prepaid X-Api-Key balance). Linked Connect keys are free. This is billing, not a side effect. Rate limit: 5/min (per API key). Tier: premium. Returns: Complete backtest results: total trades, win rate, net PnL, max drawdown, Sharpe ratio, profit factor, and individual trade log with entry/exit details. Guidelines: Compute / parse / backtest only — no live orders. Feed outputs into cc.agent_strategy with force_paper=true to paper-trade. Tags: backtest, strategy, simulation, performance, sharpe, drawdown.

  Connector

• list_goals

  Un Sdg

  List the 17 UN Sustainable Development Goals (code, title, description). Optionally drill into one goal to get its targets and indicators.

  Connector

• lnt_email_brand_guidelines

  L&T MCP

  SKILL: lnt_email_brand_guidelines Team: Platform L&T Email Brand Guidelines Call this tool to get the complete guide for 'lnt_email_brand_guidelines'. Read the 'content' field and follow its instructions. This tool takes NO parameters. Full content: --- name: lnt_email_brand_guidelines description: L&T brand guidelines for email formatting — reference document, not a function to call with parameters --- # L&T Email Brand Guidelines This is a REFERENCE DOCUMENT. Read it and use the guidelines to construct emails yourself. Do NOT call this with any arguments — it takes no parameters. ## Brand Colors - Primary Navy: #002B5C - Accent Orange: #F47B20 - Body text: #374151 - Light background: #f8fafc ## Email Structure ### 1. Header Block - Background: #002B5C (navy) - White bold text: "L&T Construction" - Subtitle: "EIP Cognitive Services Platform" in rgba(255,255,255,0.65) - Top right: orange badge (#F47B20) with text "MCP AGENT" - Below header: 4px solid orange line (#F47B20) ### 2. Greeting - "Dear [RECIPIENT_NAME]," - Color: #002B5C, bold, font-size: 16px - Padding: 32px top and sides ### 3. Body Content - Font-size: 14px, color: #374151, line-height: 1.7 - Padding: 12px 32px 24px 32px - For plain text: wrap each paragraph in p tags with margin-bottom: 12px - For structured data: use a table with navy (#002B5C) header row, white text, alternating white and #f8fafc rows - End with: "Please feel free to reach out if you need any clarification." ### 4. Divider - 1px solid #e5e7eb horizontal line ### 5. Signature Block - "Warm regards," in #374151 - Sender name in bold #002B5C, font-size: 15px - "L&T Construction — EIP Cognitive Services" in #64748b, font-size: 12px - Padding: 20px 32px ### 6. Footer Block - Background: #f8fafc - Border-top: 1px solid #e5e7eb - Centered text, font-size: 11px, color: #9ca3af - Line 1: "This email was generated by the L&T MCP Agent Platform." - Line 2: "Larsen & Toubro Limited · Construction Division · EIP Cognitive Services" - Line 3: Orange square ■ + "Confidential — For intended recipient only" ## HTML Wrapper - Full document: <!DOCTYPE html> to </html> - Body background: #f4f4f4 - Center everything in a 620px wide white table - White card with box-shadow: 0 2px 8px rgba(0,0,0,0.08) - Border-radius: 8px - All CSS must be inline — no external stylesheets ## Key Rules - From address is ALWAYS lntcs@lntecc.com - Always generate complete valid HTML - Orange accent bar between header and body is mandatory - Generate the HTML yourself from these guidelines — do not call any tool for HTML generation

  Connector

• get_dependencies

  Rubygems

  Get the runtime and development dependencies for a specific version of a Ruby gem. Returns each dependency with its version requirement string. Omit version to get the latest.

  Connector

• search

  ask

  Search the Pinnacle Ask child-development knowledge corpus (pinnacleblooms.org/ask) — real parent questions with clinically grounded, non-diagnostic answers covering speech, motor, social, cognitive, sensory, feeding and behavioural development from birth to 18 years. Returns ranked results with ids; pass a result id to `fetch` for the full answer. Optionally filter by child age in months and/or developmental domain.

  Connector

• post_lint_elixir

  webbersites-x402-data-api

  Elixir lint / debug kit: POST {code}, get the bugs back with line numbers. Deterministic static analysis — code is parsed, never executed, no AI. Catches unbalanced do/end and brackets, missing do, 'return', '+' string concat, trailing commas, field assignment, = vs == in conditions and guards, block-scoped rebinding (the classic), charlist vs String mixups, unused variables. Errors, warnings and hints with fixes. Max 128 KB. ($0.002 per call, paid via x402)

  Connector

• cc.openclaw_chat

  Central Command

  Call cc.openclaw_chat — Autonomous AI agent specialized in strategy development, backtesting, and continuous market monitoring. Uses indicator libraries, pattern recognition, and instrument specifications. Purpose: Autonomous AI agent specialized in strategy development, backtesting, and continuous market monitoring. Uses indicator libraries, pattern recognition, and instrument specifications. Behavior: conversational AI that CAN place/cancel orders and manage positions when the linked account allows it. Treat as potentially destructive. Confirm intent before asking it to trade live. Auth: X-Api-Key required (and linked exchange credentials for execution actions). Cost: $0.025 USDC per successful call (x402 Base USDC pay-per-use or prepaid X-Api-Key balance). Linked Connect keys are free. This is billing, not a side effect. Rate limit: 10/min (per API key). Tier: enterprise. Returns: Structured AI analysis with computed indicators, detected patterns, strategy recommendations, and task management for autonomous execution. Guidelines: Prefer paper/simulation paths. For live money require explicit human confirmation (confirm_live / action=execute). Report real HTTP errors; never invent proxy failures. Tags: ai, strategy, autonomous, backtesting, patterns, indicators.

  Connector

• design_session

  Colour Memory

  One-call compound tool. Submit a concept, medium, audience, and constraints — receive a complete design package: historically grounded palette, cultural narrative, commercial paint matches, WCAG accessibility check, illuminant behaviour, and a ready-made image generation prompt. Replaces chaining query_conceptual + palette_from_concept + colour_story + match_paint_system + accessibility_check + get_colour_metrics. Use when an AI agent or user needs a complete, deployable colour direction in a single call. Not for iterative refinement — use individual tools for that.

  Connector

• post_calc_finance

  webbersites-x402-data-api

  Exact financial + token math. POST {op:…}: compound (growth with per-period contributions), amortize (payment, total interest, schedule), npv, irr (deterministic bisection) — and token_units: exact decimal↔base-unit conversion via BigInt for any token decimals (ETH 18, USDC 6), the 18-decimal math that float64 silently corrupts. Iterative series computed exactly, never guessed. ($0.005 per call, paid via x402)

  Connector

• get_story_chain

  Geotone — Global News Signals

  A story timeline: the threaded developments of one multi-day event chain, oldest first (e.g. attack → casualties confirmed → international reaction). Use the chain_id values returned by get_wire. Each development is a headline + link + outlet count + tone.

  Connector

• create_lead

  Tu Lugar

  Send an inquiry on behalf of the user to the advertiser of a listing, a development project, or a real-estate company. Notifies them (email + WhatsApp) and starts a conversation. Works without an account. This sends a real message to real people — confirm the details with the user before calling.

  Connector

• search_cases

  case-doha-record

  Search 30,000+ decided public DOHA security-clearance decisions (1996 to present). Full-text query plus filters. Returns matching cases with outcome, date, guidelines, and a citable URL each.

  Connector