Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Agent Traffic Lab

REMOTE · MCP.AGENTTRAFFICLAB.COM · SCANNED SEP 27

Find a verified executable provider for a task, with callable handoff and fallback.

0 this week 72 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security57
Transport & Reachability100
Schema Quality & AI Usability67
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 713 tokens (~237/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "atl_execute" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
  • Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
Install

How do I install the Agent Traffic Lab MCP server?

Agent Traffic Lab is a hosted endpoint at https://mcp.agenttrafficlab.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · mcp.agenttrafficlab.com

# add to Claude Code
claude mcp add --transport http com-agenttrafficlab-atl 'https://mcp.agenttrafficlab.com/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "com-agenttrafficlab-atl": {
      "url": "https://mcp.agenttrafficlab.com/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "com-agenttrafficlab-atl": {
      "type": "http",
      "url": "https://mcp.agenttrafficlab.com/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.com-agenttrafficlab-atl]
url = "https://mcp.agenttrafficlab.com/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-agenttrafficlab-atl": {
      "type": "remote",
      "url": "https://mcp.agenttrafficlab.com/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add com-agenttrafficlab-atl --url 'https://mcp.agenttrafficlab.com/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  com-agenttrafficlab-atl:
    url: "https://mcp.agenttrafficlab.com/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "com-agenttrafficlab-atl": {
      "Transport": "http",
      "Url": "https://mcp.agenttrafficlab.com/mcp"
    }
  }
}
# add to Vellum
assistant mcp add com-agenttrafficlab-atl -t streamable-http -u 'https://mcp.agenttrafficlab.com/mcp'
// mcp.json
{
  "mcpServers": {
    "com-agenttrafficlab-atl": {
      "type": "http",
      "url": "https://mcp.agenttrafficlab.com/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 27 Sept 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “atl_decide” rewrote its description, which is the text the model reads security
    • Tool “atl_outcome” rewrote its description, which is the text the model reads security
    • Schema quality: 301 → 237 ▲ functional
    • Schema quality: good → excellent functional
    • Destructive annotations: pass → 0 functional
    • New tool “atl_execute” functional
  • 25 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 12 Sept 26 0
    • Stability: 0.97 → pass security
  • 11 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 8 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 6 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

  • 4 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

  • 2 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 27 Sept 2026 · Probed https://mcp.agenttrafficlab.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=mcp.agenttrafficlab.com CN=WE1,O=Google Trust Services,C=US 11 Aug 2026 9 Nov 2026 ECDSA 256 ECDSA-SHA256 4d14b841f98950fb135f5a3dc6cf818f
SANs: mcp.agenttrafficlab.com
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mcp.agenttrafficlab.com. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
agenttrafficlab.com. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.agenttrafficlab.com/mcp Verified 200
http (plaintext) http://mcp.agenttrafficlab.com/mcp HTTPS enforced 301 https://mcp.agenttrafficlab.com/mcp
MCP tools · 3 exposed · ~679 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
atl_decide ~243

Find and choose the best eligible provider, tool, or MCP route for a task when the provider is unknown. Use this for requests like 'find a provider', 'which tool should I use', 'find a fallback', 'use a cheaper, faster, or more reliable option', or when the current provider failed. Pass the task in natural language. If ATL should own execution, call atl_execute next using the returned decision_reference and outcome_correlation_token; atl_execute records the durable Outcome automatically.

NameTypeReqDescription
auth_availableboolean–Whether the caller can authenticate to the selected provider.
constraintsobject–Optional hard requirements the selected provider must meet.
desired_outcomestring–Optional result the caller wants from the task.
max_retriesinteger–Optional maximum retries allowed for the decision request.
preferencesobject–Optional trade-offs such as cost, latency, or reliability.
required_capabilitystring–Capability the selected provider must support.
taskstringyesNatural-language task. ATL infers the required capability when possible.
timeout_msinteger–Optional time limit for the decision request in milliseconds.

No output schema declared.

No examples provided.

atl_execute ~112

Execute the provider selected by a prior ATL Decision. ATL validates the execution authorization, executes the selected provider, may use bounded fallback, and automatically records the execution Outcome.

NameTypeReqDescription
decision_referencestringyesATL decision ID returned by the prior atl_decide call.
inputstringyesTask input to send to the ATL-selected provider.
outcome_correlation_tokenstringyesATL token returned with the prior decision to authorize this execution.
tenant_scopestring–Optional tenant scope for the execution authorization.

No output schema declared.

No examples provided.

atl_outcome ~324

Report the real result only when execution happened outside ATL. Use this after atl_decide if the caller executed the selected provider externally. Do not use it after atl_execute; ATL records that durable Outcome automatically. Report success, failure, timeout, payment or auth failure, unusable result, or other observed execution evidence so future routing decisions can improve.

NameTypeReqDescription
attempt_outcomesarray–Observed results for individual provider execution attempts.
cancelledboolean–Whether execution was cancelled before completion.
correlation_idstring–Caller correlation ID linking this result to related work.
decision_referencestringyesATL decision ID returned by the prior atl_decide call.
error_codestring–Provider error code observed during execution.
failure_typestring–Category of the observed execution failure.
final_provider_idstring–Provider that actually completed execution, if it changed.
http_statusinteger–HTTP status returned by the provider, when applicable.
observed_costnumber–Observed provider execution cost.
observed_latency_msnumber–Observed provider execution latency in milliseconds.
outcome_correlation_tokenstringyesATL token returned with the prior decision to authorize this outcome link.
outcome_statusstringyesFinal real-world execution result, such as SUCCESS or FAILURE.
provider_idstring–Provider selected by ATL for the prior decision.
request_idstring–Caller request ID associated with the prior ATL decision.
session_idstring–MCP session ID returned by initialize.

No output schema declared.

No examples provided.

Common questions

What is the Agent Traffic Lab MCP server?

Agent Traffic Lab is an MCP server listed in the public MCP registry as com.agenttrafficlab/atl. Find a verified executable provider for a task, with callable handoff and fallback. This page covers its hosted endpoint (https://mcp.agenttrafficlab.com/mcp).

Is the Agent Traffic Lab MCP server safe to use?

Agent Traffic Lab scores 72 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Agent Traffic Lab MCP server expose?

Agent Traffic Lab exposes 3 tools: atl_decide, atl_outcome, atl_execute. Their descriptions and schemas cost roughly 679 tokens of context every time the server is loaded.

Does the Agent Traffic Lab MCP server require authentication?

No. We connected to Agent Traffic Lab without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Agent Traffic Lab MCP server still maintained?

Agent Traffic Lab is still listed as active in the MCP registry. We last reached this channel on 27 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.