Agent Passport MCP vs Cnvs.app
A side-by-side look at the Agent Passport MCP and Cnvs.app MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Agent Passport MCP for security work as a local process; choose Cnvs.app for security over a hosted endpoint. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Agent Passport MCP when
- You need dedicated capabilities in the Security domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You want tools like
list_profiles, list_tools_for_scope, identify.
Choose Cnvs.app when
- You need dedicated capabilities in the Security domain.
- You prefer a remote HTTP/SSE transport.
- You want tools like
open_board, create_board, get_board.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Security | Security |
| Quality signal | 65/100 · Great | 59/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Remote HTTP/SSE |
| Auth | No auth required | Not declared |
| Pricing | Free | Not declared |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 4 | 1 |
| Directory activity | 5 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 152 | 25 |
| Full listing | View Agent Passport MCP | View Cnvs.app |
Tools & capabilities
Agent Passport MCP tools 152
list_profilesShow available tool profiles. Set APS_PROFILE env var to limit exposed tools (e.g. APS_PROFILE=data).list_tools_for_scopeList available MCP tools filtered by delegation scope. Pass your delegation scopes to see which tools you can use. Scopes: identity, delegation, principal, reputation, coordination, communication, governance, commerce, data, gateway, network, temporal, attribution, settlement, capability, mutual-auth. Use ['*'] for all tools.identifyIdentify yourself to the coordination server. Sets your role and scopes tools accordingly.generate_keysGenerate an Ed25519 keypair for agent identity.issue_passportIssue a complete agent passport with keys, signed passport, attestation summary, and optional values floor in a single call. The server silently captures Tier 0 observed signals and computes a passport grade (0-3). Use this to onboard any agent — no npm install required.verify_issuerVerify that a passport was officially issued by AEOESS. Checks the issuer countersignature against the published AEOESS public key. Returns false for self-signed passports.get_passport_gradeQuery the attestation grade and issuance context for a passport. Returns the passport grade (0-3), flags, and evidence summary. Grade 0 = self-signed, 1 = issuer countersigned, 2 = runtime-bound, 3 = principal-bound. This is the partner-facing trust query.list_issuance_recordsList all stored issuance records with their passport grades. Shows how many passports have been issued in this session and their trust posture. Useful for monitoring issuance patterns.get_behavioral_sequenceGet the post-issuance behavioral sequence for an agent. Shows the first 10 tool calls after passport issuance. Real agents do work. Farming agents extract. This is consilium signal #2.get_my_roleGet your current role, assigned tasks, and role-specific instructions.create_task_brief[OPERATOR] Create a new task with roles, deliverables, and acceptance criteria.assign_agent[OPERATOR] Assign an agent to a role in a task. Creates a delegation automatically.- +140 more on the listing page
Cnvs.app tools 25
open_boardALWAYS call this first when given a board URL or ID. Resolves the canonical board id and auto-creates the board row if it does not exist yet. Returns a summary (item counts, authors). After this, call BOTH `get_preview` and `get_board` before editing so you can see the layout visually AND know the exact ids/coordinates — do not skip `get_preview`, otherwise you will place new items blindly on top of existing ones.create_boardCreate a fresh board in ONE call — optionally pre-filled with content, auto-laid-out, and/or PIN-locked at create time. Mirrors the extended `POST /api/boards` REST body exactly (same server-side implementation). With no arguments it returns a blank draw board; `mode: 'todo'` (+ optional `template`) seeds a kanban board. `content` imports initial items atomically: everything is validated FIRST and the board is created only if every item passes — on any invalid item you get a structured error naming its kind + index and NOTHING is created. `autolayout: true` (draw mode) fills in x/y for texts/images that omit them (deterministic masonry grid; explicit coordinates are never touched). `lock: 'write'|'all'` locks the board atomically with creation and returns the plaintext `access_key` ONCE — there is no recovery. The response's `imported` counts confirm what was created, `ids` returns the server-minted item ids per kind in the order you supplied them (index i of `ids.texts` is the id created for `content.texts[i]`; `ids.columns` is empty when the columns came from the template seed, and lanes have no id — they are keyed by board + lane index), and `embed_url` (the `?embed=1#<id>` iframe view) is returned for any board readable without a key — it is omitted for `lock:'all'` boards, whose embed frame can't read the board anonymously. Prefer this over open_board + N per-item calls when you are building a whole board from scratch.get_boardFull structured JSON state of a board: texts (id, x, y, content, color, width, postit, author), strokes (id, points, color, author), images (id, x, y, width, height, dataUrl, thumbDataUrl, author; heavy base64 >8 kB elided to dataUrl:null, tiny images inlined). Use this for EXACT ids/coordinates/content (needed for `move`, `erase`, editing a text by id). For visual layout (where is empty space? what overlaps?) call `get_preview` instead — it's much cheaper for spatial reasoning than a huge JSON dump.get_previewCompact schematic SVG render of the board (typically a few kB even for dense boards). Returns both an image/svg+xml content block (you can SEE it) and the raw SVG text. CALL THIS any time you need to understand where things are — before placing new items, before deciding whether the canvas is crowded, before picking a free region. AI-authored items get a purple border so you can tell which contributions were yours. For precise text content prefer `get_board`.add_textCreate a NEW text node, or update an existing one (pass the same `id` to overwrite content/position in place — preferred over creating a duplicate). Supports cnvs markup (Markdown-ish) and Mermaid diagrams in the content. When using Mermaid, the ENTIRE content of this text node must be a single Mermaid diagram (one ```mermaid fenced block and nothing else — no heading, no prose before or after). If you need prose + a diagram, create two separate text nodes. `postit: true` renders as a yellow sticky; `diagram: true` renders as a framed box (2px border in the text colour, centred text) — the two are mutually exclusive. Coordinates are in board-world pixels, +x right, +y DOWN; pick a spot that does not overlap existing items (check `get_preview` first). Default width auto-fits content up to ~320 px; pass `width` for explicit wrapping (160–4096). Keep content under 100 000 chars.add_linkDrop a URL capsule onto the board — rendered as a clickable pill showing the hostname. Use this instead of `add_text` when the node is just a link; the capsule styling signals clickability to humans. Same coordinate rules as `add_text` (+x right, +y down).add_imagePlace a raster or SVG image on the board at (x, y) with explicit width/height in board pixels. `data_url` MUST be a `data:image/(png|jpeg|gif|webp|svg+xml);base64,...` string ≤ ~900 kB; hosted URLs are not accepted. Strongly recommended: also pass a tiny `thumb_data_url` (≤8 kB JPEG/PNG/WebP, ~64 px on the long edge) — it is embedded into the SVG preview so OTHER AI viewers (and you, on later `get_preview` calls) can actually see the image instead of a placeholder box.draw_strokeDraw a freehand stroke on the board. Use for arrows, underlines, connector lines, annotations, or simple shapes — a straight line needs two points, a rough circle wants ~20. Stroke width is fixed at 3 px; `color` is a NAME, not hex (case-insensitive): 'auto'/''/'black'/omitted for theme-aware ink, or 'red', 'blue', 'green', 'orange', 'yellow', 'pink', 'purple', 'maroon', 'brown', 'gray', 'lightgray', 'teal', 'sage', 'sky', 'lavender' — anything else (including a literal hex like '#ff0000') silently clamps to auto. Accepts three equivalent point formats — pick whichever your MCP client serialises cleanly: nested `[[x,y],[x,y],...]`, flat `[x1,y1,x2,y2,...]`, or a JSON string of either. Some clients (Claude Code as of 2026-04) drop nested arrays during tool-call serialisation, so prefer the flat form or the JSON-string form when in doubt. To delete a stroke later, use `erase` with `kind: 'line'` and the id returned here.moveReposition an existing item to a new (x, y) without retyping its content. Works for every item kind: `text` and `link` set the top-left to (x, y); `line` translates every point so the stroke's bounding box top-left lands at (x, y); `image` sets the top-left like text. `kind` defaults to `text` for backward compat with older callers. Find the id + kind via `get_board`. Prefer `move` over re-creating an item when only the location changes — it preserves the id, content, author and avoids a round-trip of base64 bytes for images.eraseDelete a single item by id. `kind` MUST match the item type: 'text' for text nodes, 'line' for freehand strokes, 'image' for images — the wrong kind silently targets the wrong table and is a common mistake. Get the id + type from `get_board` (texts[], lines[], images[]). There is no bulk/erase-all tool: loop if you need to delete multiple items.wait_for_updateLong-poll: blocks until the next edit lands on this board, then returns. WHEN TO CALL THIS: if your MCP client does NOT surface `notifications/resources/updated` events from `resources/subscribe` back to the model (most chat clients do not — they receive the SSE event but don't inject it into your context), this tool is how you 'wait for the human' inside a single turn. Typical flow: you draw / write what you were asked to, then instead of ending your turn you call `wait_for_update(board_id)`. When the human adds, moves, or erases something, the call returns and you refresh with `get_preview` / `get_board` and continue the collaboration. Great for turn-based interactions (games like tic-tac-toe, brainstorming where you respond to each sticky the user drops, sketch-and-feedback loops, etc.). If your client DOES deliver resource notifications natively, prefer `resources/subscribe` — it's cheaper and has no timeout ceiling. BEHAVIOUR: resolves ~3 s after the edit burst settles (same debounce as the push notifications — this is intentional so drags and long strokes collapse into one wake-up). Returns `{ updated: true, timedOut: false }` on a real edit, or `{ updated: false, timedOut: true }` if nothing happened within `timeout_ms`. On timeout, just call it again to keep waiting; chaining calls is cheap. `timeout_ms` is clamped to [1000, 55000]; default 25000 (leaves headroom under typical 60 s proxy timeouts).set_board_modeChoose whether this board is a freeform whiteboard ('draw', the default) or a kanban task board ('todo'). Mode is switchable WHENEVER the board is empty of real content: drawings (text/strokes/images) and tasks. Empty or seeded columns DON'T count (switching to 'draw' clears them), so a cleared board can be switched again, and you can flip draw<->todo freely until the first stroke/text/image or task lands. Setting 'todo' auto-seeds three starter columns (To do / In progress / Done). Returns `{ mode, columns }`. Use the task/column tools (`create_task`, `create_column`, …) once the board is in 'todo' mode.- +13 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Agent Passport MCP
{
"mcpServers": {
"aeoess-agent-passport-mcp": {
"command": "npx",
"args": [
"agent-passport-system-mcp"
]
}
}
}
Cnvs.app
{
"mcpServers": {
"cnvs-app-2": {
"url": "https://cnvs.app/mcp"
}
}
}
Frequently asked questions
Agent Passport MCP is categorized under Security and uses a local stdio subprocess. Cnvs.app belongs to Security and uses a remote HTTP/SSE transport. Pick Agent Passport MCP for security work and Cnvs.app for security.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Agent Passport MCP is listed as free. Auth: no auth required. Cnvs.app has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add aeoess-agent-passport-mcp and cnvs-app-2 as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Agent Passport MCP has a quality signal of 65/100 (Great) with 5 views, 0 installs and 4 GitHub stars. Cnvs.app has 59/100 (Good) with 1 views, 0 installs and 1 GitHub stars.