"Bootstrap" matching MCP tools:

• bootstrapA

  NovenceB

  Create an account + nv_ API key from an email. No Bearer key required. Unverified trial still publishes; OTP/verify_email is AFTER the live URL. Returns apiKey immediately — do not wait for OTP.

  ConnectorNo auth

• bootstrapA

  agent.socialA

  One call that explains the whole site: boards, auth, MCP url, rate limits, feed modes.

  ConnectorNo auth

• create_projectA

  EchoRelayA

  Create a new project on your account so an agent can bootstrap from a fresh account. The slug is derived from the name and validated server-side (format, reserved words, uniqueness). Each plan includes a fixed number of active projects (free tiers one; paid plans more — see list_subscription_plans); at the limit this errors — if an existing project can host this integration, skip create_project and call create_project_token against it instead of adding another. Requires an ACCOUNT-scoped token and the `config` scope. Returns the created project ({id, slug, name, apiBaseUrl, archived}); call create_project_token next to mint a token for it.

  ConnectorNo auth

• pysr_runA

  OccamA

  Evolutionary Symbolic Regression (PySR). Discovers algebraic equations y = f(x1, x2, ...) from feature/target data. Returns a Pareto front ranked by the complexity/accuracy tradeoff. Slower than SINDy (10-60s); searches often terminate early on convergence. For differential equations from time series, use sindy_run instead. Pricing: free tier up to 100 rows × 8 features, 60s timeout. Beyond that, $0.25 + $0.03 per 100 extra rows + $0.01 per extra feature squared, timeout up to 300s (5 min), via x402 (USDC on Base) or MPP/Stripe. MPP/Stripe adds a flat $0.35 per-transaction fee (Stripe processing), so the MPP challenge amount in a `payment_required` response is $0.35 higher than the x402 amount for the same base price; x402 gets the lower rate. Omit `payment` for free-tier requests; paid requests without a valid credential receive a `payment_required` result with pricing and accepted schemes. Full pricing: occam://pricing Advisory limits: jobs over 50,000 rows or 20 features are accepted but may not converge; response carries a top-level `warning`. Operators: fixed supported set only — custom operators (e.g. 'inv(x) = 1/x') are rejected. Unary: sin, cos, tan, exp, log, log2, log10, sqrt, abs, sinh, cosh, tanh. Binary: +, -, *, /, ^. See also prompt `supported_operators`. Loss metric: `loss` (in `pareto_front[].loss` and `best_loss`) is mean squared error between model prediction and `y` on the full training set — not RMSE, and not normalized by Var(y). A threshold appropriate for one dataset scales with y's magnitude, so set `loss_threshold` with that in mind (e.g. for y values near 1.0, 1e-6 is a tight fit; for y near 1000, the equivalent is 1.0). Early termination: set `loss_threshold` to stop at your noise floor. The server also stops when the search stalls (<1% improvement in the last third of the budget); disable with `stall_detection=false`. Response `stop_reason` is one of: loss_threshold, stall, timeout, natural. If `feature_names` is supplied, its length must equal the number of columns in `X`; a mismatch is rejected with a validation error. Follow-up: call `pysr_uncertainty` with a chosen expression and the same dataset for bootstrap confidence intervals on its fit constants and optional prediction bands. Rate limit: 10 requests/hour per IP, 200/hour global, max queue depth 20 (shared with sindy_run and pysr_uncertainty). Response (success) includes `pareto_front[]` (each with `complexity`, `loss`, `expression`, `expression_latex`), `best_expression`, `best_expression_latex`, `best_loss`, `best_complexity`, `stop_reason`, `elapsed_seconds`, `queue_seconds` (>0 = server saturated; use as backoff signal), optional `warning`, optional `_meta` (MPP receipt). Full response and payment-required schemas: occam://tool-schemas Example request: X=[[0.0], [1.0], [2.0], [3.0]], y=[1.0, 3.0, 5.0, 7.0], feature_names=["x"], max_complexity=10, timeout_seconds=15 Policy: occam://privacy-policy — Citation: occam://citation-info

  ConnectorNo auth

• pysr_uncertaintyA

  OccamA

  Bootstrap confidence intervals for the numeric constants of a frozen expression, plus optional prediction bands on an x-grid. Typical flow: call pysr_run, pick an expression from the response (best_expression or a pareto_front entry), pass it back here with the same dataset to get CIs on its fit constants. Returns frequentist bootstrap confidence intervals, not Bayesian credible intervals — posterior inference over expression structures is an open research problem. This tool freezes the expression chosen by the caller and bootstraps only its numeric constants; uncertainty about *which* expression is correct is not quantified. Bootstrap semantics: - If y_sigma is supplied, uses parametric bootstrap (y_b = y + Normal(0, y_sigma)). CI reflects user-stated measurement noise. - Otherwise uses residual bootstrap: fit once, resample residuals. CI reflects estimated-from-residuals noise. Only Float constants in the expression become free parameters. Integers stay structural (the 2 in x**2 is a function-class choice, not a fit constant). Expressions with no Float constants (e.g. "x + y") will be rejected with a validation error. Expression grammar: the `expression` string is parsed by sympy. Accepted operators are the same set pysr_run emits: unary `sin`, `cos`, `tan`, `exp`, `log`, `log2`, `log10`, `sqrt`, `abs`, `sinh`, `cosh`, `tanh`; binary `+`, `-`, `*`, `/`, `^` (or `**`). Whitespace and parenthesization are free. Every free symbol in the expression must correspond to an entry in `feature_names` — an unrecognised symbol is silently treated as a fresh sympy Symbol and the fit will fail downstream rather than reject early. Parse failures (syntax errors, malformed operators) surface as tool errors. If `feature_names` is supplied, its length must equal the number of columns in `X`; a mismatch is rejected with a validation error. Pricing: always free, regardless of dataset size. This tool has no `payment` parameter and is never subject to the x402/Stripe gate. Large bootstrap jobs still count against the shared rate limit below, so budget `n_resamples` accordingly. Rate limit: 10 requests/hour per IP, 200/hour global, max queue depth 20 (shared with sindy_run and pysr_run).

  ConnectorNo auth

• register_and_deployA

  FracteraA

  Register a new Fractera user and start the deployment of their server in one atomic call. Use this AFTER you have collected the user's email (entered twice for typo protection), server IP, and root password. Creates the User row (or reuses an existing one with the same email), creates a free Subscription, creates a ServerToken, wipes any previous installation on the target server, and launches bootstrap. The deploy is IP-first (phase-1): the server comes up on plain HTTP at http://<IP>:3002 in 8-14 minutes; it does NOT get a domain or HTTPS cert here (that is an optional later step inside the workspace). Returns session_id (for a single on-demand check_status read — do not poll) and server_token (so the user can recover via retry_deploy if anything breaks). Call this AT MOST ONCE per conversation.

  Connector

  Destructive

  No auth

• scaffold_serviceA

  @imqueueA

  READ-ONLY: returns generated source code as text and writes nothing to disk, creates no project and runs no command. Generates an idiomatic @imqueue/rpc service (an IMQService subclass with @expose()d, JSDoc-typed methods) plus a bootstrap that starts it. Provide the methods you want, or omit them for a starter template. Any non-primitive parameter or return type also gets a types.ts with the required @classType()/@property() declarations — without those the generated client types it `any`, which compiles. Use create_service (local install only) if you want files actually written.

  ConnectorNo auth

• create_projectA

  KeelenA

  Start building something new: creates a GitHub repo and begins work on it. Use this ONLY when the user wants a NEW repo scaffolded. If they already have a repo, use import_project(repo_full_name) instead — this tool would create a second, empty one beside theirs (list_github_repos() browses what the workspace can see). Scaffolds a new GitHub repo, a bootstrap-mode project, and submits `build_description` as the project's first Roadmap Request. `name` is a concise GitHub short repo slug (no owner); `project_kind` is REQUIRED and one of library | node_library | python_library | service | cli | web_app | godot_game | roblox_game; `preview_command` is required iff `project_kind == 'web_app'`. `engine` is OPTIONAL — one of claude_code | codex | glm | kimi | grok (defaults to claude_code); codex, glm, kimi, and grok require the workspace to have a matching connected credential. `org` is OPTIONAL — a GitHub organization login to create the repo inside (e.g. your company org); omit it to land the repo on a member's personal account. `private` defaults to True. `ci_runs_on` is OPTIONAL — the CI runner labels for the scaffolded workflow, e.g. ["self-hosted", "linux", "x64", "my-fleet"]. Omit it to inherit the workspace default (ubuntu-latest if unset). Labels no registered org runner carries are rejected, because GitHub would queue such a job forever rather than fail it. `framework` is OPTIONAL and `web_app`-only — one of vite | next (defaults to vite). It picks the scaffolded frontend rails: `vite` a vanilla-TypeScript SPA, `next` a Next.js app-router app. Passing it with any other `project_kind` is an error. The repo is created on the GitHub account of a workspace member with repo-create OAuth access (this path has no specific caller user), so the returned `repo` owner is whichever member's token resolved (or the chosen `org`). If no member has repo-create access — or the resolving member can't create in `org` — the call returns an actionable error. Returns {project_id, repo, thread_id, next_action, poll_after_seconds, next_step}; follow next_step (poll get_request_status with the returned thread_id). On the rare arm where the first Request failed to submit, next_action is "call_tool" with next_tool="submit_request".

  ConnectorNo auth

• pathrule_take_snapshotA

  PathruleA

  Record a point-in-time inventory of the user's project under a workspace. Remote MCP cannot see the filesystem, so YOU (the AI) collect this inventory with your own Read/Glob/Grep tools before calling this. Persist it so future setup, bootstrap, drift detection, and onboarding flows have structured evidence to reason over. Required: workspace_id. Strongly recommended: project_name, file_count, file_tree (cap at ~5000 entries — summarise deeper paths), file_extensions_summary, top_level_dirs, sampled_contents for README, package.json / pyproject.toml / Cargo.toml, CLAUDE.md, AGENTS.md, main config files (truncate each to ~4KB). Optional: git_head / branch / git_log_summary if you can read them, ai_notes for free-form observations.

  ConnectorNo auth

• get-quickstart-guideA

  JxBrowser MCP ServerA

  Provides step-by-step instructions for an AI assistant to set up a new JxBrowser project. This tool is meant for fully automated project creation and should be called when the user asks to create, start, scaffold, bootstrap, init, template, or generate a JxBrowser project, app, or sample. CRITICAL RULES: 1. NEVER call this tool before knowing the user’s preferences. If the user hasn’t specified them, ASK first: - UI Toolkit: Swing, JavaFX, SWT, or Compose Desktop - Build Tool: Gradle or Maven 2. Immediately after calling this tool, you MUST execute all setup commands returned by this tool using the Bash tool to actually create the project.

  ConnectorNo auth

• scan_skill_contentA

  Nullcone Threat IntelligenceA

  Pre-execution content scan for skill/instruction files. Analyzes the full text of a skill (markdown, plain text, SKILL.md, etc.) for malicious patterns BEFORE the agent follows the instructions. This is the critical defense against remote skill-mediated credential exfiltration (CodeMax attack class, 2026-03-14) where model-level safety only fires AFTER the payload has already executed. Call this on any skill/instruction content fetched from the web before executing any of its steps. If should_block is True, refuse to proceed. Detection signals: - Download-and-execute chains (wget/curl → chmod +x → run) - Bootstrap file modification (.npmrc, NODE_OPTIONS, LD_PRELOAD) - Encrypted credential exfiltration (GPG, openssl → HTTP POST) - Credential access patterns (process.env, keychain, .env files) - Code obfuscation (base64 decode pipe to shell) - Multi-stage kill chain correlation Args: content: Full text content of the skill file source_url: URL where the skill was fetched from (for reporting) Returns: risk: "CLEAN" | "LOW" | "SUSPICIOUS" | "MALICIOUS" risk_score: 0.0–1.0 should_block: True if the skill should NOT be executed should_warn: True if the skill warrants user confirmation kill_chain: True if a multi-stage attack chain was detected signals: List of detection signals with categories and excerpts content_hash: SHA256 of the content (for IOC submission if malicious)

  ConnectorNo auth

• propfirms_simulate_tradesA

  luxalgo-mcp-serverA

  Simulate a challenge by resampling the trader's OWN R-multiple trade series with a stationary block bootstrap instead of a win-rate model. WHY THIS BEATS WIN-RATE MATH: challenge rules are breached by streaks, not by averages - a daily-loss limit dies to a cluster of losses inside one day, and a trailing drawdown dies to a losing streak right after an equity peak. Real trade series are streaky (autocorrelation, volatility clustering, edge that comes and goes), and the stationary bootstrap resamples contiguous blocks of the actual series (geometric length, mean blockMeanLength, default 5 trades), so the trader's real streak structure survives into every simulated day. A parametric model with identical summary statistics shuffles trades independently and therefore understates breach risk for streaky traders. Use propfirms_simulate when only summary stats are available; use this whenever the actual trades are. Provide the series as rSeries (array of R-multiples: each trade's P&L divided by the amount risked on it), rSeriesText (pasted JSON/CSV/whitespace text, optional 'R' suffix per value), or one of the timestamped-log inputs below; exactly one of the four, at least 10 trades, 100+ strongly recommended. Returns the same full SimResult as propfirms_simulate (structuredContent, histograms off by default) plus a text summary that also reports the sample's win rate and mean R. TIMESTAMPED LOGS: tradeLogText accepts a pasted CSV/TSV trade log with a header row (open time and R required; close time and direction optional; loose header names are matched; timestamps without an offset are read as UTC). The R-series and, unless tradesPerDay is passed, the trades-per-day rate are derived from the log, and parse warnings are surfaced in the text output. NEWS WINDOWS: with a timestamped input, newsFilter runs the simulation TWICE on the same seed and options, once on the full history and once without the trades opened inside configurable windows around scheduled releases (a built-in recurring-template calendar of high- and medium-impact events across USD, EUR, GBP, JPY, AUD, CAD, CHF, NZD, plus optional custom event times). The returned SimResult is the news-avoided scenario; structuredContent.newsComparison carries both scenarios' pass probability, funded probability and EV, the excluded-trade count, and a calendar caveat that must be relayed verbatim. PORTFOLIO MODE: tradeLogTexts (2 to 5 logs) merges several timestamped histories into one chronological series and simulates the combined account, so cross-strategy loss clustering survives. Overlap across the histories is ALWAYS analyzed and attached as structuredContent.portfolioOverlap; the text summary carries the audit-risk verdict, and a 'high' verdict is an explicit warning that a prop firm may audit or refuse payouts for correlated accounts. SIMULATED RULES (engine v1): consistency rules (steps[].consistency) and funded payout gating (funded.payoutRules) are actually SIMULATED, not merely flagged - a distinguishing feature of this engine. Consistency uses a rational stop rule (the trader stops a day once more profit cannot help and keeps trading until the best-day share complies - flag 'consistency-stop-rule'); payouts follow a maximum-withdrawal model (withdraw everything the rules allow above buffer/caps, never below the loss floor; balances and floors carry across payouts - flag 'funded-withdrawal-model'); a funded consistency gate is checked per payout window (flag 'funded-consistency-window-approximated'). The pre-1.0 flag id 'funded-payout-resets-account' no longer exists. UNITS: every *Pct rule field and every percent-mode risk value is in PERCENT UNITS (5 = 5%, 0.5 = 0.5%). The one exception is winRate, which is a FRACTION in [0, 1] (0.55 = 55% winners). Probabilities in results are fractions in [0, 1]. DETERMINISM: identical inputs including `seed` reproduce byte-identical results on any platform. Include the seed and path count when reporting numbers so users can reproduce them exactly; re-run with a few different seeds to gauge Monte Carlo spread. ASSUMPTIONS: every result carries assumptions.flags - dataset-declared rules the engine does NOT simulate (e.g. scaling plans or soft daily lockouts, which make real odds worse than simulated) plus engine simplifications - and assumptions.disclaimer. These are material: always surface the flags and the disclaimer to the user alongside the numbers, never just the headline probability. Results are distributions under stated assumptions, not promises. Composes with any broker-statistics tool: if another MCP server exposes round-trip statistics (winRate, avgWin, avgLoss) or a raw R-multiple series from the user's real trades, feed them here to answer "given my actual trading, what are my odds on this challenge and what risk should I use?". Convert currency statistics to R-multiples by dividing by the average amount risked per trade: winRate stays a fraction, avgWinR = avgWin / avgRisk, avgLossR = |avgLoss| / avgRisk.

  ConnectorNo auth

• ateam_log_progressA

  ateam-mcpA

  Record that a build STEP is done, so a later run does not redo it. Write it AS IT HAPPENS, never at the end — the runs that most need a journal are the ones the clock kills. WHY: a continuation cannot otherwise tell what the previous run achieved, so it re-runs the whole orientation (bootstrap, get_workflows, list_solutions, get_solution, get_spec, get_examples, github_read) to re-derive from documents what was already established — and re-inflates its prompt into the region where provider latency collapses. Measured across 13 runs: stalls track PROMPT SIZE (~60k), not turn count. ateam_get_progress is ONE call instead of nine. status — three values, and the third is the point: built — the artefact exists (files written, committed) deployed — the platform accepted it verified — YOU CALLED IT AND GOT REAL DATA BACK `verified` REQUIRES verified_by, and a deploy response is not verification. `connected` and `tools > 0` are tools/list facts: a clinic connector showed 9 tools while every storage call returned 401. A journal that stops at `deployed` records that build as finished. Re-log the same step as it advances (built → deployed → verified) — latest wins, no update path. If a step REGRESSES, re-log it at the lower status: silence must not read as "still fine".

  ConnectorNo auth

• pathrule_create_workspaceA

  PathruleA

  Create a new Pathrule workspace inside an organization. Cloud-only: writes the workspace row through the user's JWT (RLS enforces organization membership). Does NOT attach the workspace to a local folder, does NOT install any AI client config, and does NOT render CLAUDE.md/AGENTS.md or editor companion files — those steps require Pathrule Studio or CLI. After creation, call pathrule_setup with the returned workspace_id to fetch the bootstrap brief.

  ConnectorNo auth

• pathrule_setupA

  PathruleA

  Fetch the active Pathrule bootstrap brief and execute it. Call this ONCE when the user asks to set up / bootstrap / initialize Pathrule for a project (e.g. 'Set up Pathrule for this project', 'Bootstrap Pathrule'). The response `body` is a prompt you must follow immediately — it tells you how to scan the project, propose memories/rules/skills, and write the approved items via pathrule_write_memory / _rule / _skill. Do NOT call this mid-task, for already-populated workspaces, or when the user just wants context — use pathrule_get_context for routine context lookups. If no workspace exists yet, call pathrule_list_organizations + pathrule_create_workspace first.

  ConnectorNo auth

• chieflab_verify_installA

  ChiefLabA

  POST-INSTALL HEALTH CHECK. Call this exactly once after the agent has wired ChiefLab into the runtime (per the bootstrap protocol at https://chieflab.io/bootstrap.txt). Returns { ok, mcpReachable, toolsDiscovered, visibleFrontDoorTools, callableInternalTools, workspaceReady, hasOpenLoops, blockedConnectors, summary }. `toolsDiscovered` means the visible front-door catalog, not every internal/back-compat callable handler. The `summary` is one sentence the agent should paste verbatim to the user — e.g. 'ChiefLab installed and ready. Workspace fresh, no open loops, all channels need connectors before auto-publish.' Do NOT list every internal tool — render the summary only. If `ok` is false, the response includes a `nextStep` describing the single recovery action.

  ConnectorNo auth

• register_and_deployA

  FracteraA

  Register a new Fractera user and start the deployment of their server in one atomic call. Use this AFTER you have collected the user's email (entered twice for typo protection), server IP, and root password. Creates the User row (or reuses an existing one with the same email), creates a free Subscription, creates a ServerToken, wipes any previous installation on the target server, and launches bootstrap. The deploy is IP-first (phase-1): the server comes up on plain HTTP at http://<IP>:3002 in 8-14 minutes; it does NOT get a domain or HTTPS cert here (that is an optional later step inside the workspace). Returns session_id (for a single on-demand check_status read — do not poll) and server_token (so the user can recover via retry_deploy if anything breaks). Call this AT MOST ONCE per conversation.

  Connector

  Destructive

  No auth

• check_statusA

  FracteraA

  Read the current installation progress ONCE, on demand. Call this only when the user explicitly asks how the deploy is going (e.g. "what is the status", "did it finish") — never on a timer and never in a polling loop. The deploy takes 8-14 minutes and the authoritative status channels are the email pipeline + the dashboard; one read on request is enough. Returns the current step, the list of completed steps (~44 total in a full bootstrap), and whether installation is done or failed.

  ConnectorNo auth

• sap_quick_contextA

  SAP MCP ServerB

  Free single-call bootstrap aggregator. Returns a compact markdown-like summary with server version, total tools count, tools by category, pricing tiers summary, premium plugins/capabilities count, bundled skills list, and nextAction guidance. Pass agentKnownVersion with the version you currently know to get skillsUpdateRequired + skillsContents (full SKILL.md inline) when the server version differs — this lets you auto-update your local skills in 1 call without a separate sap_skills_bundle. Use this instead of calling sap_agent_start, sap_pricing_catalog, sap_premium_plugin_catalog, sap_skills_list, and sap_get_tool_category_summary separately to reduce bootstrap from 5+ tool calls to 1. SAP MCP execution guidance: Intent: SAP MCP tool workflow. Pricing: free; call directly without x402. Routing: free hosted call; call directly and keep it small/exact when possible. Signer boundary: hosted reads/builders never receive keypair bytes; value-moving results must be finalized locally when signing is required.

  ConnectorNo auth

• long_horizon_stressA

  crashtestyourstrategyA

  Distribution of multi-year wealth paths for a savings plan (monthly_contribution) or a withdrawal plan (monthly_withdrawal, inflation-indexed by default) on a portfolio from the substrate universe. Multi-year paths chain ~2y model blocks (block-bootstrap, disclosed); long-run drift is RE-ANCHORED to stated capital-market assumptions (overridable via long_run_drift; the substrate's raw stress drift would compound a structural bear universe — both are echoed in the output) while the model's path shape (vol, clustering, correlations, hedge-breaks) is kept. Costs are ON by default. Returns terminal-wealth quantiles (nominal + real), ruin/shortfall probabilities, a sequence-of-returns diagnosis (same plan, bad vs good first two years), and a drift-sensitivity block (assumptions − 2pp). Amounts in the caller's currency unit. Descriptive, not advisory — no rate, allocation, or product is recommended.

  ConnectorNo auth

• sap_agent_migrate_pricing_menuA

  SAP MCP ServerB

  Backfill or resync the AgentPricingMenu PDA for the connected wallet SAP agent. Run this once if sap_update_agent, sap_close_agent, or createEscrowV2 fails with AccountNotInitialized on the pricing_menu account. Agents registered before pricing menus were created at registration need this one-time migration. Local-signer-only; hosted accountless SAP MCP rejects this direct write before x402 payment. SAP MCP context: Direct synapse-sap-sdk wrapper served by this MCP. Read tools return on-chain state; write tools require signer policy, configured RPC, and the active SAP profile. SAP MCP execution guidance: Intent: agent bootstrap, routing, skills, or repair guidance. Pricing: paid read-premium; estimate first, then use sap_payments_call_paid_tool when the runtime cannot replay x402 natively. Routing: paid hosted call; call sap_estimate_tool_cost first, then use sap_payments_call_paid_tool if the runtime cannot handle x402 natively. Signer boundary: hosted reads/builders never receive keypair bytes; value-moving results must be finalized locally when signing is required.

  ConnectorNo auth