Public product, pricing, workflow, and API reference for the Cannon Studio AI video production platform.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 1 month ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The cannon-studio MCP server exposes 15 tools, focused primarily on web capabilities. Its published description reads: "Public product, pricing, workflow, and API reference for the Cannon Studio AI video production platform". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates cannon-studio F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Cross-tool shadowing" and "Cross-tool shadowing". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check cannon-studio's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add cannon-studio to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://www.cannonstudio.app/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Search public Cannon Studio knowledge when a user asks about products, workflows, pricing, models, comparisons, use cases, or developer API docs. Public read-only: no auth, no state changes, no charge
Fetch one public Cannon Studio knowledge record by id after search. Public read-only: no auth, no state changes, no charges; use search first when you do not already have a record id.
List public Cannon Studio capabilities for an audience, workflow, or output type. Public read-only: no auth, no state changes, no charges; use search or fetch when the user needs deeper source text.
Recommend a Cannon Studio workflow for a stated creative or developer goal. Public read-only: no auth, no state changes, no charges; use this for planning, not to create generation jobs.
Compare Cannon Studio's fit against named alternatives for a use case. Public read-only: no auth, no state changes, no charges; it returns approved positioning and cautions agents not to invent compet
Explain public Cannon Studio pricing, credits, plans, and usage tradeoffs. Public read-only: no auth, no state changes, no charges; use list_offerings or get_checkout_link only when the user asks for
List public Cannon Studio plans, credit packs, and team offerings. Public read-only: no auth, no state changes, no charges; returns first-party checkout or inquiry URLs without creating Stripe session
Return the first-party Cannon Studio checkout or inquiry URL for a selected offering. Public read-only: no auth, no state changes, no charges; use list_offerings first to get a valid product_key.
List public Cannon Studio model availability by product surface. Public read-only: no auth, no state changes, no charges; model availability is surface-specific and does not guarantee account eligibil
List first-party Cannon Studio image, video, audio, subtitle, editing, Composer, and 3D toolkit surfaces, including which ones are developer-API operations and which should be opened in the app or rou
Return public docs for Cannon Studio developer API operations and payload shapes. Public read-only: no auth, no state changes, no charges; use this before estimate_generation_cost or create_generation
Check authenticated Cannon Studio account/API connectivity before estimating or creating requests. Requires OAuth or a developer API key; may update key/token usage metadata, but does not spend credit
Estimate credits for a Cannon Studio generation request before creating billable work. Requires OAuth or a developer API key; it may update key/token usage metadata but does not spend credits, enqueue
Create billable async Cannon Studio generation work only after explicit user approval. Requires OAuth or a developer API key; can spend credits up to max_credits and cannot be cancelled through MCP af
Poll and sync an existing Cannon Studio generation request by id. Requires OAuth or a developer API key; not a pure read because it may update lastPolledAt, sync downstream task state, update logs, an
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: search
A tool description tries to alter the model’s use of another tool.
o charges; call fetch with a returned id when full source-backed textRecommendationDescriptions must describe only their own tool.
tool: fetch
A tool description tries to alter the model’s use of another tool.
ord by id after search. Public read-only: no auth, no state changes, nRecommendationDescriptions must describe only their own tool.
tool: list_capabilities
A tool description tries to alter the model’s use of another tool.
no charges; use search or fetch when the user needs deeper source textRecommendationDescriptions must describe only their own tool.
tool: get_pricing_context
A tool description tries to alter the model’s use of another tool.
no charges; use list_offerings or get_checkout_link only when the user asks foRecommendationDescriptions must describe only their own tool.
tool: get_checkout_link
A tool description tries to alter the model’s use of another tool.
no charges; use list_offerings first to get a valid product_key.RecommendationDescriptions must describe only their own tool.
tool: list_toolkits
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "project_context_only"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: get_api_operation
A tool description tries to alter the model’s use of another tool.
use this before estimate_generation_cost or create_generation_request when operation/inpRecommendationDescriptions must describe only their own tool.
tool: estimate_generation_cost
A tool description tries to alter the model’s use of another tool.
nge assets. Use get_api_operation first if operation or input fields are unclear,RecommendationDescriptions must describe only their own tool.
tool: create_generation_request
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "webhook_url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: create_generation_request
A tool description tries to alter the model’s use of another tool.
submission. Use estimate_generation_cost first, then set confirmed=true and a user-approRecommendationDescriptions must describe only their own tool.
tool: get_generation_request
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
or a developer API key; not a pure read because it may update lastPollRecommendationRemove side-channel parameters; constrain tool inputs.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
estions. Prefer search and fetch for citation-friendly answers. Do notRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: create_generation_request
The server advertises open-world / broadly-scoped capabilities.
annotations.destructiveHint = trueRecommendationScope tools to the minimum needed.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.