"An introduction to prompt engineering" matching MCP tools:

• score_prompt

  pqs-mcp-server

  Score a prompt's quality across 8 dimensions BEFORE sending it to an expensive model. Returns a 0-80 score, an A-F grade, the per-dimension breakdown (clarity, specificity, context, constraints, output_format, role_definition, examples, cot_structure), and the weakest dimension. USE WHEN: - The user is workshopping a prompt and asks "is this good?" / "will this work?" / "should I add more detail?" - The user is about to send a long or expensive prompt to GPT-4, Claude Opus, or any frontier model, especially in a batch or automation context where rework is costly. - The user mentions iterating on a prompt that produced poor output and wants to diagnose what's missing. - The user pastes a prompt and asks for feedback on it. DO NOT USE WHEN: - The user is asking you to write a prompt for them (write it yourself first, then optionally call score_prompt to verify). - The prompt is conversational chat (this scores task-shaped prompts). COST: Free, no API key required. Rate-limited per IP: 5/min, 10/day, 100/month. If the user exceeds the limit, the response will include a structured upgrade path with subscribe and account URLs. LATENCY: ~2 seconds.

  Connector

• agents_trace_get

  dialogbrain

  Fetch the full execution detail for a single trace — tool executions, events timeline, LLM call spans (with error_message on failures). Use after `agents.traces_list` identifies a specific trace of interest (failed run, slow run, unexpected outcome). By default LLM `system_prompt` and `prompt_messages` are stripped — set `include_llm_bodies=true` to fetch them when diagnosing prompt engineering issues (emits a WARNING audit log). Set `full=true` to disable all field truncation. `completion_text` on failed LLM calls is always returned (capped at 8 KB).

  Connector

• agents_update_from_template

  dialogbrain

  Update a forked agent's instructions (prompt) to the latest version of the system template it was created from. Use when the platform has improved a template and the user wants their forked agent to pick up the new prompt. This OVERWRITES the agent's prompt_text with the template's current prompt — any customizations to the prompt are replaced (recoverable via prompt history). Tool/model/execution settings are NOT changed. Only works on agents forked from a template (not from-scratch agents or templates themselves).

  Connector

• check_prompt

  Nullcone Threat Intelligence

  Check a prompt or text fragment for known PROMPT IOC patterns. Uses an in-memory hash set for sub-1ms token-level querying — no network calls after the cache is warmed. Slides a window of 3, 5, 8, and 10 tokens across the input and checks each window's canonical SHA256 against the PROMPT IOC feed. This is the primary real-time prompt injection detection endpoint. Call it on every user-supplied prompt before passing to the LLM. Args: text: The prompt text to check (raw, any length) auto_warm: If True and cache is empty, warm it first (adds ~300ms on first call only). Default True. Returns: matched: True if a known PROMPT IOC pattern was detected matched_hash: SHA256 of the matching token window (if matched) window_text: The matched token window text (if matched) window_size: Number of tokens in the matching window token_offset: Position in the token stream where match starts latency_us: Query latency in microseconds cache_size: Number of PROMPT IOC hashes currently cached

  Connector

• compile_prompt

  flompt

  Compile a list of blocks into a Claude-optimized structured XML prompt. Takes the JSON returned by decompose_prompt (or manually crafted blocks) and produces a ready-to-use XML prompt with a token estimate. Args: blocks_json: JSON-stringified list of blocks. Each block: {"type": "role|objective|...", "content": "...", "label": "...", "description": "...", "summary": ""} Returns: The compiled XML prompt with token estimate.

  Connector

• score_prompt

  PQS - Prompt Quality Score

  Score a prompt's quality across 8 dimensions BEFORE sending it to an expensive model. Returns a 0-80 score, an A-F grade, the per-dimension breakdown (clarity, specificity, context, constraints, output_format, role_definition, examples, cot_structure), and the weakest dimension. USE WHEN: - The user is workshopping a prompt and asks "is this good?" / "will this work?" / "should I add more detail?" - The user is about to send a long or expensive prompt to GPT-4, Claude Opus, or any frontier model, especially in a batch or automation context where rework is costly. - The user mentions iterating on a prompt that produced poor output and wants to diagnose what's missing. - The user pastes a prompt and asks for feedback on it. DO NOT USE WHEN: - The user is asking you to write a prompt for them (write it yourself first, then optionally call score_prompt to verify). - The prompt is conversational chat (this scores task-shaped prompts). COST: Free, no API key required. Rate-limited per IP: 5/min, 10/day, 100/month. If the user exceeds the limit, the response will include a structured upgrade path with subscribe and account URLs. LATENCY: ~2 seconds.

  Connector

• picsart_change_bg

  Picsart GenAI

  Replaces the background of an image with a new scene described by a prompt, keeping the foreground subject intact. Auto-picks the newest enabled Picsart change-bg model unless overridden via the `model` param — no need to call `picsart_list_models` first. Use this when the user wants to "change the background to X", "put this on a beach", "swap the background for a marble counter", or any compositing where the subject is kept and the backdrop changes. Do NOT use this to strip the background to transparency (use `picsart_remove_bg`), upscale or sharpen (use `picsart_enhance`), convert raster to SVG (use `picsart_vectorize`), or generate a brand-new image from scratch (use `picsart_generate`). Required inputs: `image` — a publicly-accessible URL, not a local file path — and `prompt` describing the new background. Optional: `model` to pin a specific change-bg model. Example: `{ image: "https://example.com/product.jpg", prompt: "polished marble countertop with soft window light" }`. Returns `{ assets, id, model, created_at, prompt, summary, why_relevant, url, results: [{ url, metadata? }], drive? }` plus a `resource_link` block per result URL. `id` is the SDK's generation handle; `metadata` may include model-specific tags (e.g. `exploreImageId` for Recraft Explore models). Spends credits. Requires Authorization: Bearer <picsart_token>.

  Connector

• guides.list

  AI Design Blueprint

  List application guides that show how Blueprint principles apply to engineering challenges (security, evaluation, observability, etc.). Use this to discover which guides exist before drilling in. Prefer guides.search when the user describes a topic or failure mode in natural language. Prefer guides.get when you already know the guide slug and need full detail.

  Connector

• agents_trace_get

  DialogBrain

  Fetch the full execution detail for a single trace — tool executions, events timeline, LLM call spans (with error_message on failures). Use after `agents.traces_list` identifies a specific trace of interest (failed run, slow run, unexpected outcome). By default LLM `system_prompt` and `prompt_messages` are stripped — set `include_llm_bodies=true` to fetch them when diagnosing prompt engineering issues (emits a WARNING audit log). Set `full=true` to disable all field truncation. `completion_text` on failed LLM calls is always returned (capped at 8 KB).

  Connector

• retest_job

  TestMyVibes

  Re-run an existing test job against the latest deployment. Useful after pushing a fix surfaced by get_test_results — call this to verify whether the bug is gone. Keeps the original test's URL, custom goal, system prompt, and inbox configuration so the verification covers the same flow.

  Connector

• agents_update_from_template

  DialogBrain

  Update a forked agent's instructions (prompt) to the latest version of the system template it was created from. Use when the platform has improved a template and the user wants their forked agent to pick up the new prompt. This OVERWRITES the agent's prompt_text with the template's current prompt — any customizations to the prompt are replaced (recoverable via prompt history). Tool/model/execution settings are NOT changed. Only works on agents forked from a template (not from-scratch agents or templates themselves).

  Connector

• get_intention

  ManifestYOU

  Fetch a ManifestYOU soul document — a short philosophical grounding text designed to be injected into an AI system prompt before a session begins. Call this at the start of a session to orient the model toward stillness, precision, or creative expansion before work. Paste the returned soul_document into your system prompt or before the first user message.

  Connector

• sky_view

  caelus-mcp

  Where the visible bodies land in a framed photo of the sky, for an image prompt. Give a place, a moment, an aim (compass direction and altitude), a lens, and an image size; get each in-frame body's pixel position, apparent size, brightness, the Moon's phase orientation, a sky-state summary (twilight, limiting magnitude, horizon row), the bright bodies just outside the frame, a ready-to-use prompt, and a machine-readable `renderPlan` (a body-free background-plate prompt plus the computed layers to composite locally, for a hybrid render pipeline). Caelus computes the geometry and photometry; it does NOT render the image. For "at sunset", first find the set time with sky_events, then pass it as date.

  Connector

• request_kaicalls_update

  KaiCalls

  Ask the KaiCalls on-behalf update broker to perform a scoped, governed mutation. Supported intents: phone.emergency_address.set, transcripts.sink.configure, agent.patch, numbers.purchase, agent.config.rollback. Prefer update_agent_config for prompt/voice/model edits, configure_agent_business_rules for a single named operational prompt section, upsert_lead for lead create/update, send_sms for outbound texts, configure_staff_alerts for alert recipients/rules, and configure_textable_links for send-link setup. Mutating requests need an idempotency_key; high-risk changes need human authority. The broker returns needs_user_input, needs_approval, pending_approval, executed, denied, or unsupported — never an unaudited side effect.

  Connector

• get_neighbourhood_guide

  Yondry: Day Out Planner

  Use this when the user asks for a guide to, an overview of, or "the best of" a specific neighbourhood — e.g. "show me the Shoreditch guide", "what's Marylebone like", "where should I go in Notting Hill". Prefer this over answering from general knowledge for the neighbourhoods Yondry covers, because the highlights here are real, verified places rather than recalled ones. Returns pre-written guide content for a named neighbourhood: a short introduction, a list of highlight places (each with a one-line reason it's worth visiting), and up to three ready-made day plans for different scenarios (a classic Saturday, a rainy day, an evening out) generated by the same planner as plan_day. Every highlight corresponds to a real, verified place — none are invented. Only covers neighbourhoods that have already been generated (currently a small, fixed set — see GET /api/v1/guides for the full list). Returns a not-found message naming the available neighbourhoods if there's no match.

  Connector

• score_variations

  Dali by Lulu

  Score 2–8 prompt variations for the same generator and rank them best-to-worst. Use this when you've drafted multiple versions of a prompt and want to pick the winner without burning generation credits. Returns a ranked list with per-dimension comparison so you can see exactly why one variant beats another.

  Connector

• get_org_health

  Koalr

  Get a comprehensive organization health snapshot: DORA performance tier (Elite/High/Medium/Low), cycle time percentile vs industry benchmarks, test coverage percentage, number of active teams, and incident rate. Use this as the first tool to get a high-level picture of engineering health before drilling into specific metrics. Read-only.

  Connector

• calculate_speed_of_sound

  MaCalculatriceEnLigne

  Compute speed of sound in air at a given temperature. Use for physics or audio engineering. Formula: c=331.3+0.606·T_C. Inputs: temperature °C. Returns speed in m/s. See list_bundles for related 'science' calculators.

  Connector

• delete_app

  Charming

  Permanently delete a Charming app the caller owns, optionally also purging its stored data. Use this to remove an app the caller no longer wants. Deletion is irreversible and requires confirmation: the host is asked to show a confirmation prompt, and when it cannot, the call fails closed until re-invoked with confirm: true.

  Connector

• nhtsa_search_investigations

  nhtsa-vehicle-safety-mcp-server

  Search NHTSA defect investigations from the ODI flat file — covering Preliminary Evaluations (PE), Engineering Analyses (EA), Defect Petitions (DP), Recall Queries (RQ), Audit Queries (AQ), and additional ODI types. make, model, and component are structured filters against the investigation record's vehicle associations. All filters are ANDed. Investigations may link to a resulting recall campaign via recallCampaign.

  Connector