Skip to content

ai.getvda/integration-agent

by getvda.ai · remote · no sign-in to list tools · v1.0.0 · published by ai.getvda

Integration Agent

Changes · 3
CompareRegistry entry

6 tools: 3 change things and 3 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http integration-agent https://drift.getvda.ai/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

6 tools

Changes things 3Claude Code: ask
  • drift_checkFREE.Can send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    FREE. Has this MCP server's declared tool surface changed since we first saw it? Returns the current hash, when it last changed, how many times, and the Witness seal for the latest change.
  • drift_hashFREE.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    FREE. Canonically hash a tool list you supply, so you can confirm your implementation reproduces our bytes before trusting any hash we publish. ensure_ascii=False is the flag people miss.
  • selftestFREE, no payment required.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    FREE, no payment required. Runs this agent's real capability on a fixed canned input and returns the genuine result, an honest assertion grade, and the full trust manifest (signed Agent Card, JWKS, governance/licence chain, safety posture) with a proof link for every claim. Intended for registries, graders and auditors: this is behavioural evidence, not a self-description.
Only reads 3Claude Code: allow, ask for 2 outbound
  • drift_diffWhat actually changed: field-level detail for this server's observed changes, including which tool moved and whether the change touched a description, a schema or an annotation.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "drift_diff" says "diff": a word for reading.

    What it can reach

    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    What actually changed: field-level detail for this server's observed changes, including which tool moved and whether the change touched a description, a schema or an annotation.
  • drift_probeFetch this server RIGHT NOW and compare it to our stored baseline.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The description's first verb is "fetch": a word for reading.

    What it can reach

    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Fetch this server RIGHT NOW and compare it to our stored baseline. Use when you need a fresh answer rather than the last scheduled observation.
  • drift_statusFREE.No findings

    Why it is in this group

    • The name "drift_status" says "status": a word for reading.
    Description, as the server wrote it
    FREE. Coverage of the MCP Drift Observatory: how many public MCP servers we have discovered, how many we can actually observe, and how many are auth-walled. Reports the denominator, not just the flattering numerator.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out3
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Looked at Oct 22, 2026, 15:24 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
3
Protocol version
2026-07-28
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
none
RFC 9728 protected resource metadata
none
Authorization servers
none
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://drift.getvda.ai/mcp: tools/list returned 6 tools to an anonymous client, including drift_hash (write), drift_check (write), selftest (write)

    What this check looks for

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http integration-agent https://drift.getvda.ai/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__integration-agent__drift_status"
    ],
    "ask": [
      "mcp__integration-agent__drift_hash",
      "mcp__integration-agent__drift_check",
      "mcp__integration-agent__drift_diff",
      "mcp__integration-agent__drift_probe",
      "mcp__integration-agent__selftest"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as integration-agent. Review it before you use it.

Capability tags behind 3 rules
  • mcp__integration-agent__drift_check outbound
  • mcp__integration-agent__drift_diff untrusted-input, outbound
  • mcp__integration-agent__drift_probe untrusted-input, outbound