Tyton

This connector has been deprecated

This is a duplicate listing. Use Tyton instead, which follows Tyton's entry in the official MCP Registry.

Submit code findings

submit_findings

DestructiveIdempotent

Saves code review findings from the customer's repository to the audit: server-side events, dedup IDs, Pixel and container presence, payment provider, framework, backend location and existing Conversions API quality, plus the relative paths reviewed and any inapplicable checks with reasons. Unknown values stay unknown, not failed. Findings are stored as agent-reported, not verified deployed behavior. A group label is a label only; each report stays separate. Returns the updated audit decision and report link.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "submit_findings"
  }
}

Input Schema

Name	Required	Description
`url`	Yes	the site these findings belong to
`group`	No	legacy grouping label only; does not combine reports or verify domain ownership
`notes`	No	anything else found; a string or an array of strings
`backend`	No	where the backend code is: in this repo, a separate repo not available here, or unknown
`audit_id`	No	audit run ID returned by Tyton; each audit run has its own ID
`revision`	No	latest run revision; 0 for the first write of a new audit session, then the revision returned by the previous write
`audit_key`	No	private audit write capability returned by Tyton; a secret that authorizes changes to this audit only
`dedup_ids`	No	orderId/event_id on both browser and server events?
`framework`	No	frontend framework (from package.json deps)
`request_id`	No	UUID identifying one mutation; a repeated request_id with identical content is treated as a retry
`existing_capi`	No	grades for existing CAPI code, if any: hashes_pii (does it hash emails/phones before sending?), sends_event_id (does each server event include an event_id?), graph_version (which Graph API version, e.g. v19.0), test_event_code_in_prod (is a test code left in production?), sends_fbp_fbc (are browser cookie values forwarded?)
`pixel_in_code`	No	Meta Pixel initialized anywhere in the code?
`not_applicable`	No	Inapplicable checks, each with the actual reason, based on reviewed files and confirmed scope. Missing access counts as unknown, not N/A.
`reviewed_files`	No	relative paths actually inspected in the relevant customer repository; no source code, absolute paths or secret files
`server_evidence`	No	one line: file/function where it was found
`checkout_domains`	No	domains the checkout lives on, if separate; no customer paths or query strings
`payment_provider`	No	payment processor used (from package.json, env vars, webhook routes)
`container_in_code`	No	Tyton container script embedded?
`server_side_events`	No	code sends server-side events (CAPI/SDK/webhook)? unknown when not checked

Output Schema

Name	Required	Description	Default
`url`	Yes
`kind`	Yes
`source`	Yes
`status`	Yes
`context`	No
`session`	No
`decision`	No
`findings`	Yes
`inventory`	No
`reportUrl`	No
`capturedAt`	Yes
`components`	No
`limitations`	Yes
`nextActions`	Yes
`reportSaved`	Yes
`observations`	No
`schemaVersion`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 18, 2026

TDQS

A3.7/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=false, so the safety profile is partly covered. The description adds genuinely non-structured context: findings are stored as "agent-reported, not verified deployed behavior", a group label does not merge reports, and it returns the updated audit decision plus report link. It still does not say what a write overwrites or how a mismatched revision is handled.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the purpose and keeps three short sentences, with the trust caveat ("agent-reported, not verified") placed early where it matters. The first sentence is a dense comma-run listing many data categories, but for a 19-parameter ingestion tool that enumeration earns its length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-value detail is not required, yet the description still tells the agent it gets back an updated audit decision and report link. Combined with the trust model, group semantics and unknown-handling rules, an agent has enough to call a complex nested-object tool correctly; only the write/overwrite and revision-conflict behavior remain unstated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% with 19 well-documented properties, many with their own enums and per-field notes, so the schema carries the parameter burden and baseline 3 applies. The description's parameter-level remarks (group is label-only, unknown != failed) largely restate what the schema already says ("legacy grouping label only; does not combine reports"), adding little beyond it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource pair ("Saves code review findings ... to the audit") and enumerates exactly which findings are captured (server-side events, dedup IDs, Pixel/container presence, payment provider, framework, backend location, existing CAPI quality, reviewed paths, N/A checks). This distinguishes it from read-side siblings like read_audit, though it does not explicitly contrast with the other write-side siblings such as record_audit_context or record_audit_runtime.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied through field-level guidance ("Unknown values stay unknown, not failed", "Missing access counts as unknown, not N/A") which tells the agent how to fill the report, but there is no statement of when to call this versus begin_audit, record_audit_context, or save_audit_to_project. No prerequisites about needing audit_id/audit_key/revision are called out as a gating sequence.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Tyton tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?