"A simple MCP server to serve images from a filesystem path with appropriate MIME type" matching MCP tools:

• ag_json_diffA

  agent-guildB

  Structural diff of two JSON values with per-path changes. Compares two JSON values and returns added/removed/changed paths (JSON-Pointer-style), capped at 500 changes. Use to verify an agent's output changed only what it was asked to. Deterministic, fixture-verified, free for guests (rate-limited; pass your Guild api_key to use your member budget). Returns the result plus a Guild-signed provenance envelope. `payload` MUST match this JSON Schema: {"type": "object", "properties": {"a": {}, "b": {}}, "required": ["a", "b"], "additionalProperties": false} Output schema: {"type": "object", "properties": {"equal": {"type": "boolean"}, "changes": {"type": "array"}, "change_count": {"type": "integer"}}, "required": ["equal", "changes", "change_count"], "additionalProperties": false}

  ConnectorNo auth

• read_fileA

  BorealHostB

  Read the contents of a file from a site's container. Max file size: 512KB. Binary files are rejected — use the site's file manager or SSH for binary files. Requires: API key with read scope. Args: slug: Site identifier path: Relative path to the file Returns: {"path": "wp-config.php", "content": "<?php ...", "size": 1234, "encoding": "utf-8"} Errors: NOT_FOUND: File doesn't exist VALIDATION_ERROR: File is binary or exceeds 512KB

  ConnectorNo auth

• upload_fileA

  BorealHostB

  Upload a base64-encoded file to a site's container. Use this for binary files (images, archives, fonts, etc.). For text files, prefer write_file(). Requires: API key with write scope. Args: slug: Site identifier path: Relative path including filename (e.g. "images/logo.png") content_b64: Base64-encoded file content Returns: {"success": true, "path": "images/logo.png", "size": 45678} Errors: VALIDATION_ERROR: Invalid base64 encoding FORBIDDEN: Protected system path

  ConnectorNo auth

• word_createA

  Local MCPB

  Creates a new Word (.docx) document at `path` with the given text content (and an optional title rendered as the heading). The path must be somewhere LMCP can write; Desktop/Documents/Downloads may need a one-time Files-and-Folders grant (System Settings → Privacy & Security → Files and Folders). Returns {created, path}. For a OneDrive or Google Drive path use onedrive_write_file / gdrive_write_file; to append to an existing doc use word_append, to read one word_read.

  Connector

  Destructive

  OAuth

• interest_rateA

  mcpA

  Use this when you need the exact interest rate that grows a principal to a target amount over a set number of years. type="compound" (default) uses the closed-form nth-root formula for the given compounding frequency; type="simple" uses linear growth. Requires target greater than principal and all values positive. Returns the annual rate as a percent plus the interest earned and the growth multiple; compoundingPerYear is null for simple interest. Deterministic: same input, same output. Example: principal=1000, target=2000, years=10, compoundingPerYear=12 -> ratePercent=6.9515, growthMultiple=2. Prefer this over trial-and-error.

  ConnectorNo auth

• analyze_reviewA

  ListingGood MCPA

  Analyze a negative Amazon review for root cause and a suggested response (async; 2 credits). Extracts the underlying issue from a critical review and drafts a brand-appropriate response angle. Use this after a negative review appears, to decide how to reply. Do NOT use it to generate a listing or an appeal - use generate_listing or generate_poa for those. Read-only; deducts 2 credits; runs asynchronously, poll for the result. Args: text: the negative review text (required). marketplace: marketplace code (default US). lang: zh or en (default en).

  ConnectorNo auth

• query_knowledge_graphA

  Analytics Legends — SAP AI & Analytics MCP ServerA

  The RELATIONS between the platform's teaching objects — which Academy module teaches which concept, which study covers which module, what a concept relates to. THIS IS THE ONLY TOOL ON THIS SERVER THAT SERVES EDGES; the others serve rows. Ask it what connects to what, not what exists. SCOPE, AND IT IS NARROWER THAN 'the knowledge graph': it carries four node types — `concept`, `module`, `study`, `vendor` — and every edge whose BOTH endpoints are one of them. The whole graph holds twelve node types; the eight it does not carry are each either served by their own tool or named as not served at all, and `_meta.excluded_node_types` says which per type (consultant data is served at NO tier), so a missing type is a documented boundary and never a silent gap. Call it with `node_id` (e.g. `module:M178`, `concept:C001`, `study:ai-impact-2026-EN`) to walk one node's neighbourhood; with `node_type` and/or `query` to find a node id first. `edge_type` and `direction` narrow a walk. Read `_meta.available_edge_types` — computed from the served projection on every call — before assuming an edge type exists.

  ConnectorNo auth

• xer_parserA

  Critical Path PartnersA

  Parse a Primavera P6 XER file and return a TABLE SUMMARY (not the full row-level data — XER row dumps explode the MCP context window). For each table in the XER, returns the table name, field list, and record count. Per-row data is intentionally omitted — for forensic / DCMA / windows analysis use the dedicated tools (``forensic_windows_analysis``, ``critical_path_validator``, etc.) which consume the parsed XER internally and return analytical summaries, not raw rows. Use this tool to confirm an XER is parseable, list its tables, see the data date / project name from PROJECT, or count activities in TASK before deciding which deeper tool to run. Args: xer_path: server-side filesystem path to the XER file. xer_content: full text of the XER file (alternative for hosted/remote use). Supply EXACTLY ONE of path/content. Returns: { "filepath": absolute path, "encoding_used": "utf-8" | "cp1252" | ..., "ermhdr": file header dict (P6 version, export user, etc.), "tables": [{"name", "fields", "record_count"}, ...], "table_count": int, "total_records": int, "project_summary": { "proj_id", "proj_short_name", "proj_long_name", "data_date", "plan_end_date" } (from first PROJECT row, if any) }

  ConnectorNo auth

• goal-read-evidence-contentA

  Planner MCP — provable "done" for AI agentsA

  Read attached evidence through MCP without changing its format. Pass evidenceId from goal-get. Text (text/plain, JSON, NDJSON) returns newline-preserving redacted lines; offset/limit are zero-based line pagination. Images return a native MCP image with original MIME and bytes. For a complete video, PDF, ZIP or other binary, binaryDelivery=link (default) returns a resource_link to the authenticated original download — no base64 and no conversion. If the client cannot open external links, binaryDelivery=base64 embeds the exact original bytes in a resource blob; this expands data by about 33% plus JSON overhead and can consume the client context window, so use it only when needed. byteOffset/byteLimit require binaryDelivery=base64. Text secrets are redacted; binary evidence is unmodified.

  ConnectorNo auth

• goal-read-evidence-contentA

  Planner (proof-of-done)A

  Read attached evidence through MCP without changing its format. Pass evidenceId from goal-get. Text (text/plain, JSON, NDJSON) returns newline-preserving redacted lines; offset/limit are zero-based line pagination. Images return a native MCP image with original MIME and bytes. For a complete video, PDF, ZIP or other binary, binaryDelivery=link (default) returns a resource_link to the authenticated original download — no base64 and no conversion. If the client cannot open external links, binaryDelivery=base64 embeds the exact original bytes in a resource blob; this expands data by about 33% plus JSON overhead and can consume the client context window, so use it only when needed. byteOffset/byteLimit require binaryDelivery=base64. Text secrets are redacted; binary evidence is unmodified.

  ConnectorNo auth

• get_hero_pathsA

  VA Heroes PH — From Zero to Hero | Become a Virtual AssistantA

  Retrieve every publicly published VA Heroes PH Hero Path — the career and training tracks a Filipino virtual assistant can start with or specialise in — so an agent can help a visitor identify a suitable path. Use it when someone asks what programs, tracks, specialisations or career options VA Heroes PH offers, or to obtain a slug before calling get_hero_path. Requires no input; optional filters are 'type' ('training' for VA skill paths, 'sales' for the Loan Officer path), 'featured' (only the recommended starting path) and 'limit' (1-100). Returns { total, count, items[] } where each item has slug, name, label, tagline, description, intro, highlights, type, featured, externalUrl and canonical url. It does NOT return pricing, schedules, enrolment status, applicant records or any private data, and it cannot submit an application.

  ConnectorNo auth

• web_to_markdownA

  Ciro Cesar Maciel — Free ToolsA

  Fetches a public web page and returns its content as clean Markdown. WHEN TO USE: you need to read a page — documentation, an article, a product page — to answer, summarize or quote it; or the user wants a page as Markdown. HOW IT WORKS: - url: a public http(s) address. Private networks, localhost and addresses with credentials are refused. - Reads the HTML the server sends (like a simple browser, without running JavaScript). Pages that build their content with JavaScript have no text to convert — the error says so. - onlyMainContent (default true) drops menus, headers, footers, sidebars, cookie banners and ads. Set false to keep the whole page. - pages above 1 also follows links on the same site (same folder and below), breadth-first, up to that many pages (max 20), respecting robots.txt. Slower: a few seconds per page. - Limits per page: 15 seconds and 5 MB. PDFs and non-HTML files are not converted. RETURNS: for each page, its Markdown with absolute links and images, plus title, description and language when the page has them; pages that failed are listed with the reason. link: this tool's web page with the same request. ERRORS say why the page could not be read and whether retrying makes sense.

  ConnectorNo auth

• get_attachment_upload_urlA

  GrigoraB

  Get a one-time upload link for a LOCAL file to attach to create_website / edit_website. MCP cannot carry files, so a local file goes straight from disk to Grigora's storage with the returned `curl` command (replace <LOCAL_FILE_PATH> with the file's path and run it in a shell). The file's contents never pass through the conversation. Then put the returned `url` in the attachments list of create_website or edit_website. The link expires in 15 minutes; one link per file. Allowed: images (PNG, JPG, WebP, GIF, AVIF), PDF, CSV (up to 10 MB), and audio/video (up to 80 MB). For a file that is already online, skip this and pass its public URL directly. Args: file_name: The file's name, e.g. "brand-guide.pdf" (refer to it by this name in the prompt). mime_type: e.g. "image/png", "application/pdf", "text/csv", "video/mp4". size_bytes: The file's exact size in bytes (e.g. from `wc -c < FILE`).

  ConnectorOAuth

• lab_identitaet_pruefenA

  FilmLabA

  Check whether still images of a project show the SAME character as its character sheet — before paid clips are made from them. Each image is compared against the sheet's detail and fullbody views. It judges identity (species, build, colouring, head shape, large markings), NOT style, light, pose, place or props — and deliberately NOT micro details like an ear notch or the number of fingers, which no image model holds reliably. Free. Runs in the BACKGROUND: returns a `job_id` with HTTP 202 — poll it with lab_get_job until status is done|failed; the result lists per image passt, sicherheit, abweichungen, begruendung (or error). Up to 16 images and frames together per call. Images must be completed images of this project (imported images are refused). To check frames of a GENERATED CLIP (an orbit turnaround, a lab_animate clip) pass clip_frames: the clip's video_id and the seconds to cut out — the frames are taken from the clip itself and compared the same way; a second beyond the clip's end fails only that frame. The sheet needs a reference image (lab_generate_character_reference).

  ConnectorOAuth

• asterwise_get_angel_number_personalA

  AsterwiseA

  Computes a personal angel number from a birth date using the Pythagorean Life Path as the base. Life Path 1-9 maps to the triple sequence (LP 4 → 444). Master numbers 11, 22, 33 map to 1111, 2222, 3333 respectively. WORKFLOW: BEFORE: RECOMMENDED — asterwise_get_numerology_profile — confirm Life Path before calling. AFTER: None. INPUT CONTRACT: date: Birth date in YYYY-MM-DD format. Example: '1994-03-31' name (optional): Person's name for personalisation. DO NOT CONFUSE WITH: asterwise_get_angel_number_today — collective daily number from today's date, not birth date. asterwise_get_numerology_profile — full Pythagorean profile; this tool extracts only the Life Path → angel sequence mapping. Full output and error contract: https://docs.asterwise.com/mcp/tools/get-angel-number-personal/

  ConnectorOAuth

• query_docs_filesystem_honeydew_documentationA

  Honeydew AI DocumentationA

  Run a read-only shell-like query against a virtualized, in-memory filesystem rooted at `/` that contains ONLY the Honeydew Documentation documentation pages. 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 to `head` or `cat` — a page at the URL path `/some/page` lives at `/some/page.mdx`. To search the docs with exact keyword or regex matches, use `rg`. To understand the docs structure, use `tree` or `ls`. **Paths are specific to this site — never guess them.** Discover real paths with `tree / -L 2`, `ls /`, or the search tool before reading. If a path does not exist, that only means the guess was wrong; it does NOT mean the topic is undocumented — use `rg -il "keyword" /` to find where it is covered. **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 /some-directory && ls` or `ls /some-directory`). Do NOT assume that `cd` in one call affects the next call. Examples (replace the placeholder paths with real ones from `tree` or search): - `tree / -L 2` — see the top-level directory layout - `rg -il "rate limit" /` — find all files mentioning "rate limit" - `rg -C 3 "apiKey" /some-directory/` — show matches with 3 lines of context around each hit - `head -80 /some/page.mdx` — read the top 80 lines of a specific page - `head -80 /page-one.mdx /page-two.mdx /section/page-three.mdx` — read multiple pages in one call - `cat /some/page.mdx` — read a full page when you need everything 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, `/some/page.mdx` becomes `/some/page`.

  ConnectorNo auth

• fvs_download_final_videoA

  Future Video StudioA

  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

  Destructive

  No auth

• update_listing_imagesA

  TeppekA

  Add and/or remove photos on one of the USER'S OWN existing listings (max 6 total). First call request_image_upload for each new image and upload the bytes, then pass the returned keys in `add`; a key with no uploaded file fails with image_not_uploaded. Adding any image re-triggers AI moderation — the listing returns to 'pending' until the new images are cleared. Removing images leaves a live listing live; on a pending or rejected listing it requests a new moderation verdict. Free (no credit).

  ConnectorNo auth

• approve_physical_task_completionA

  Molt2MeetA

  Approve a completed task — SIMPLE FLOW ONLY. Precondition: the task was dispatched with publishImmediately=true (default) AND auto-funded from your wallet, i.e. you did NOT call request_task_quote/fund_task/publish_task (escrow flow). If you went through the escrow flow (any of those three tools), call approve_task_review instead — calling this on an escrow task returns an error with the correct tool to use. Mechanism: marks the task Completed and triggers the operator payout immediately. There is no review window for the simple flow. Task must be in ProofUploaded or UnderReview status. Requires: API key from register_agent. Next: monitor task.settled and task.closed via get_task_events — settlement happens automatically.

  ConnectorNo auth

• stream_taskA

  TunnelMind Data APIB

  Opens a persistent SSE connection that emits events as the task progresses. The stream closes automatically when the task reaches a terminal state or after ~90 seconds (timeout). Heartbeat comments are sent every ~15 seconds to keep the connection alive through proxies. Event types: - `status` — emitted when status changes (pending → running → complete/failed) - `result` — emitted on `complete` with the full result payload - `error` — emitted on `failed`, `cancelled`, or `expired` with error info - SSE comment (`: heartbeat`) — keepalive, no data Use this tool when: - You want real-time progress without polling. - You are in an environment that supports SSE (EventSource API). Do NOT use this tool when: - You want a simple one-shot status check — use `get_task` instead. - Your HTTP client doesn't support streaming responses. Inputs: - `task_id` (path, required): 26-char ULID. Returns: - SSE stream (`text/event-stream`). Each event is `event: <type>\\ndata: <json>\\n\\n`. Cost: - Free. Counts as one request against rate limits when the stream opens. Latency: - First event: <200ms. Stream duration: up to 90s.

  ConnectorNo auth

• render_previewA

  kernelCADA

  Use this when you need to LOOK at a kernelCAD model — render its script to deterministic PNG views for visual self-check (the visual half of the evaluate → render → inspect → fix loop), with NO studio or dev server required. Pass { code } (inline source) or { file } (a .kcad.ts path), exactly one. Renders the canonical engineering views (front, right, top, iso — pass { views } for a subset, e.g. ["iso"] for fastest iteration) plus an optional { pose: "<az>,<el>" } arbitrary camera angle (degrees; az=0,el=0 is front, +az rotates CCW around +Z, +el lifts the camera). NO STUDIO / DEV-SERVER REQUIRED: a prebuilt static player (dist/headless-player) is served from an ephemeral local port automatically; a running studio dev server is used as fallback, and { base_url } forces one. The only environment dependency is playwright chromium (npx playwright install chromium). Pass { focus } or { hide } (arrays of feature ids or assembly part names, mutually exclusive) to isolate parts — same semantics as `kernelcad render --focus/--hide`. Pass { section: { axis, position, flip? } } to cut a cross-section and inspect INTERIOR geometry (wall thickness, internal pockets, whether a bore runs through) rather than only the outer shell. Pass { explode: { factor, mode? } } to pull a multi-part assembly apart (mode: "mate-axis" default, or "radial") using the same mesher as `kernelcad render --explode` — requires assembly.model()/solvedModel(). PNGs are written to { out_dir } (default: a fresh temp session directory) and returned as absolute paths with per-view camera descriptions (kernelCAD is Z-up). Mechanism truth runs first, same protocol as `kernelcad render`: a broken mechanism still renders but every tile is watermarked MECHANISM BROKEN (KERNELCAD_RENDER_STRICT=1 refuses instead); read { mechanism, mechanism_failure_codes }. The probe runs full BREP interference sweeps and can dominate latency on large assemblies — pass { no_mechanism_check: true } for fast iteration (the preview then reports mechanism: "unverified"; ignored under strict mode). Pass { overlay: 'zebra' | 'curvature' | 'continuity' } for a surface-quality visualisation (zebra stripes from vertex normals, curvature as vertex colours, continuity edges coloured by G0/G1/G2/broken) — numbers come from inspect({ of: 'continuity' | 'curvature' }); the overlay is the picture. PUBLISH PRESET: pass { preset: 'publish' } for a share-ready studio product shot (gallery tile, social post, README image, product page): key/fill/rim lights + room reflections, soft contact shadow, clean backdrop ({ background: 'white' (default) | 'light' | 'dark' | 'black' | '#rrggbb' | 'transparent' } — transparent gives a PNG with alpha), { shadow: false } to drop the shadow, 2× supersampled anti-aliasing, 30° lens, the model silhouette centred and auto-framed with ~11% air (a script's setCameraTarget is ignored), per-part colours/materials as authored, no watermark. With no views/pose it renders ONE image named 'hero' (3/4 front-right, az=30°, el=22°) at 1600×1200; width/height go up to 2048; views/pose still work under the preset. Output is deterministic for the same input. For a 360° loop use capture_animation({ turntable: true }). INSPECTION SHEET: { sheet: true } renders all seven views (iso, front, back, left, right, top, bottom) and adds one labelled image named 'sheet' tiling them — do not call a model done because it compiled; call it done when every tile of the sheet matches the request. Returns { ok, images: [{ name, path, description }], out_dir, bounds, mechanism, render_source, render_ms, diagnostics }. PATHS ARE LOCAL to the machine running the MCP server — local stdio clients read them directly; hosted/remote clients should use open_in_studio instead. Hosted server: the PNGs come back IN the result as image content (up to ~1.5 MB total; larger sets are link-only) and each `images[i].url` is an HTTPS link that expires after 24 h. `images[].path` is a server-side path you cannot open. Works without saving a project (autosave:false is fine). Hosted: lib.fromSTEP / fromSTL / fromDXF / fromSVG and referenceImage take a direct string literal or a const bound to one (computed expressions are unsupported). They accept "asset:<id>" (from request_upload), an https:// URL or a data: URI as the path.

  ConnectorNo auth