cleartrace MCP server
com.cleartracedata/cleartracecleartracedata.comstreamable-httpv1.0.0Scanned
Neutral on-chain execution benchmarking: slippage, revert rates, MEV, and DEX frontend attribution.
7 tools: 6 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
6 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the cleartrace MCP server can do
The cleartrace MCP server is published by cleartracedata.com, a domain the MCP Registry verified. It has 7 tools. It can create or change data (6 tools: execution_benchmarks, revert_rates, attribution, contract_attribution and 2 more), but cannot delete data. 1 tool only reads.
None of its tools reads private data, brings in text other people write, or sends data out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 12, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
7 tools
Changes things 6Claude Code: ask
attributionWhich frontend, router or interface originated on-chain DEX volume, aggregated per contract per chain.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 Which frontend, router or interface originated on-chain DEX volume, aggregated per contract per chain. This is the dataset ClearTrace exists for: it names the venue behind volume that block explorers leave as an anonymous contract. THE VOLUME COLUMNS ARE TWO DIFFERENT KINDS AND MUST NOT BE SUMMED TOGETHER. `direct_volume_usd`, `aggregator_volume_usd`, `proxy_volume_usd` and `aggregator_partner_volume_usd` partition `total_volume_usd` between them. `calldata_suffix_volume_usd` and `erc20_fee_volume_usd` are OVERLAYS: they re-describe dollars already counted in the first group, seen through a different attribution vector. A suffix figure larger than the total is therefore correct and is not a bug. Adding an overlay to a partition column double-counts. Volumes refresh weekly and are dated to the Monday of their window, so present them as a week's volume and never as today's.
contract_attributionWhat ClearTrace knows about a single contract or wallet address: its per-chain volume split across the four attribution vectors, plus any label resolved for it.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 What ClearTrace knows about a single contract or wallet address: its per-chain volume split across the four attribution vectors, plus any label resolved for it. Most useful on the ANONYMOUS routers and proxies that aggregate views leave unnamed -- that is the differentiated question this answers. Known, named protocol contracts are often keyed by name rather than address upstream and may return nothing here, so an empty result for a famous router is not evidence the address is obscure. An address that resolves to no label is reported with a null label. Report that as 'not identified', which is what it means: these are genuinely anonymous deployments, and guessing an operator from volume or deployer alone has been wrong before.
execution_benchmarksRank DEXs and aggregators by realized execution quality: median slippage against a minute-level off-chain reference price (Dune prices.usd, an interpolated 5-minute exchange-aggreg…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 Rank DEXs and aggregators by realized execution quality: median slippage against a minute-level off-chain reference price (Dune prices.usd, an interpolated 5-minute exchange-aggregate feed and not a VWAP), expressed as a score of 0-100 (higher means less slippage). This score measures SLIPPAGE ONLY. Revert rates and MEV exposure are tracked as separate metrics and are deliberately not folded in, so do not present this as an overall 'best execution' ranking -- a venue can score well here and fail often, and the caller has to ask `revert_rates` to find that out. Execution quality is not uniform across chains: pass a chain for a single-chain ranking, or 'all' for the blended cross-chain rollup, and do not describe the blend as if it were one chain's result.
gas_pricesCurrent gas price on each supported chain, from RPC.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 Current gas price on each supported chain, from RPC. On the L2s (Base, Arbitrum, Optimism) this is the EXECUTION gas price only and excludes the L1 data availability fee, which is a real and sometimes dominant part of an L2 transaction's cost. Any cost estimate built from this figure on an L2 is a lower bound and should be labelled as one; comparing an L2 'cost' against Ethereum's on this basis overstates the L2's advantage.
request_api_keyMint a free API key that multiplies this server's rate limits by 10x.No findings
Why it is in this group
- The name "request_api_key" says "request": a word for a change.
Description, as the server wrote it Mint a free API key that multiplies this server's rate limits by 10x. Requires an email address. The key changes LIMITS ONLY. Every figure served here is public and identical with or without one, there is no paid tier, and no data is gated behind it -- so present this as raising a ceiling, never as unlocking content. Ask the user before submitting their email; do not invent an address to satisfy the argument. The key is returned once and cannot be shown again, so surface it to the user verbatim.
revert_ratesThe share of a venue's routing transactions that fail on-chain, per chain.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 The share of a venue's routing transactions that fail on-chain, per chain. Reported separately from slippage because reliability and price are different questions. DO NOT RANK ACROSS EXECUTION MODELS. A revert rate measures reliability only where the failing transaction is the user's own -- a 'router' venue, where the user signs and submits the swap. On a batch-auction or intent venue a solver settles, and an order that cannot be filled never becomes a transaction at all, so its on-chain revert rate is structurally near zero no matter how well or badly it fills. Sorting every venue by revert rate puts those at the top and means nothing. `comparable_only` (the default) returns only the rows that may legitimately be ranked against each other. Read `user_revert_rate_pct` when present: the headline rate on some cells stays inflated by address-rotating spam senders that no per-sender filter separates cleanly, and the user-only figure is the measured genuine-user experience. Each row carries its `execution_model` and a `revert_comparable` flag; quote them.
Only reads 1Show 1 read-only tool
explain_transactionClassify a single transaction against the attribution engine: which frontend or router originated the trade and by which evidence, the pools it touched, any fee recipients, and whe…No findings
Why it is in this group
- The name "explain_transaction" says "explain": a word for reading.
Description, as the server wrote it Classify a single transaction against the attribution engine: which frontend or router originated the trade and by which evidence, the pools it touched, any fee recipients, and whether it was sandwiched. Confidence is per-vector and is reported per result -- a calldata suffix is strong evidence a specific frontend tagged the swap, while a fee recipient is indirect evidence and is never rated high. Pass that qualification through instead of stating the frontend flatly. `estimated_volume_usd` (only with price=true) is a best-effort spot price on the dominant leg. It is an approximation for orientation and must never be quoted as a settlement figure. Fee amounts are exact raw token integers with no decimals or pricing applied. deep=true costs more upstream credits; leave it off unless a shallow classification came back unattributed.
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 or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- 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 Nov 20, 2026, 18:36 UTC, unchanged since Oct 29, 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
- 6
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- 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 6 tools that change things (6 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://cleartracedata.com/mcp: tools/list returned 7 tools to an anonymous client, including execution_benchmarks (write), revert_rates (write), attribution (write), contract_attribution (write), gas_prices (write) and 1 more
Posture changes
- Oct 29, 2026
- Reachable: no to yes
- HTTP status of an anonymous initialize: none to 200
- tools/list served without credentials: no to yes
- Tools that change things, listed without credentials: 0 to 6
- Protocol version: none to 2025-06-18
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Reachable: no -> yes; HTTP status of an anonymous initialize: none -> 200; tools/list served without credentials: no -> yes (and 2 more).View diff
- Reachable: no to yes
- HTTP status of an anonymous initialize: none to 200
- tools/list served without credentials: no to yes
- Tools that change things, listed without credentials: 0 to 6
- Protocol version: none to 2025-06-18
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http cleartrace https://cleartracedata.com/mcpclaude mcp add --transport http cleartrace https://cleartracedata.com/mcpRun 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.
{
"permissions": {
"allow": [
"mcp__cleartrace__explain_transaction"
],
"ask": [
"mcp__cleartrace__execution_benchmarks",
"mcp__cleartrace__revert_rates",
"mcp__cleartrace__attribution",
"mcp__cleartrace__contract_attribution",
"mcp__cleartrace__gas_prices",
"mcp__cleartrace__request_api_key"
],
"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 cleartrace. Review it before you use it.
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.cleartracedata/cleartrace/verify?hash=0a670ce7ef300abe648b75def31748627d6d1df574182f3760e48af4cd5c513a" | jq -e '.changed == false'Pinned hash 0a670ce7ef30, from Nov 12, 2026, 21:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.cleartracedata/cleartrace/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.cleartracedata/cleartrace)Source: MCP Registry. Synced Oct 21, 2026, 17:53 UTC.
cleartrace MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the cleartrace MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 6 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the cleartrace MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the cleartrace MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the cleartrace MCP server have?
- 7 tools: 6 write, 1 read. execution_benchmarks, revert_rates, attribution, contract_attribution, gas_prices, request_api_key and explain_transaction.
Does the cleartrace MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the cleartrace MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the cleartrace MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 12, 2026.