Basis Protocol MCP server
io.github.basis-protocol/basisbasis-protocolstreamable-httpv1.0.0Scanned
Attested risk scores for stablecoins, DeFi protocols and wallets, with receipts.
7 tools: 4 change things and 3 only read.
- Reads private data · 1
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
4 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 Basis Protocol MCP server can do
The Basis Protocol MCP server is published by the GitHub account basis-protocol. It has 7 tools. It can create or change data (4 tools: basis_data, basis_answer, receipt_verify and score_history), but cannot delete data. 3 tools only read.
1 tool reads private data (entity_read).
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, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 16, 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 4Claude Code: ask
basis_answerAsk the Basis Agent a question about attested risk state.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 Ask the Basis Agent a question about attested risk state. Answers cite attestation hashes; ungroundable queries are refused. Never recommends positions or forecasts. Pass your hub API key (x-api-key header or ?apikey=) to attribute reads. Multi-turn: pass the envelope's session_id back as session_id. Parameters: query: The question (max 4000 chars). session_id: Session UUID from a previous envelope (optional).
basis_dataMarket, governance and risk data in one tool.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 Market, governance and risk data in one tool. Pick a kind: liquidity_depth (entity=coin id), yield_data (entity=protocol, optional), governance_activity (entity=protocol slug; window=days, 90), bridge_flows (entity=bridge id, optional), exchange_health (entity=exchange id, optional), volatility (entity=asset id), incidents (entity=entity id, optional), peg_monitor (summary of latest deviation + status per coin; detail=true with entity returns that coin's 5-minute series, window=hours, 24), venue_shift (entity=operator slug, optional), asset_footprint (entity=token or symbol), divergence (capital-flow vs quality signals; severity=notable|alert|critical, limit=20, window=hours 24), treasury_events (entity=wallet, optional), riskiest_wallets (limit=20), scoring_backlog (limit=20), record (the delegation record as the five questions — terms, conduct, holdings, soundness, exposure, visibility; entity=node_class:native_id e.g. sky_star:grove, stablecoin:usds, morpho_vault:8453:0x..., tokenized_fund:ethereum:0x...; a bare entity searches by name; severity=SCO60|MICA67|GENIUS adds a lens verdict per held stablecoin), shock (entity=token contract address; window=shock in bps, 1000: the loss followed through holders, gross, after pro-rata exit capacity, and bounded by declared caps). Responses are capped near 12 KB; an unknown kind returns the list of kinds.
receipt_verifyVerify a receipt or citation hash from an envelope (basis_answer, entity_read).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 Verify a receipt or citation hash from an envelope (basis_answer, entity_read). Resolves it against the attestation tables and returns what it attests to, or that it is unknown. ``source`` optionally restricts the table.
score_historyDaily SII score history for a stablecoin: a list of {date, score, grade} only.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 Daily SII score history for a stablecoin: a list of {date, score, grade} only. Parameters: coin: symbol, slug or contract address (resolved like entity_read) days: lookback window, 1-365 (default 30)
Only reads 3Show 3 read-only tools
entity_readLook up any entity by symbol, slug, contract/wallet address, operator or vault name.Reads private dataNo findings
Why it is in this group
- The name "entity_read" says "read": a word for reading.
What it can reach
- private-dataThe description's first sentence says "vault": it reads secrets.
Description, as the server wrote it Look up any entity by symbol, slug, contract/wallet address, operator or vault name. Returns {entity_type, id, score, grade, confidence, report_hash, receipt_hash, links, receipt}. report_hash is the entity's latest attested report; receipt_hash is a deprecated alias of it. receipt is this answer's own receipt (check it at receipt.status). When nothing resolves returns {match: null, did_you_mean: [up to 5 candidates], receipt} rather than an error.
get_methodologyThe Basis methodology.No findings
Why it is in this group
- The name "get_methodology" says "get": a word for reading.
Description, as the server wrote it The Basis methodology. mode="summary" (default): index list, versions, component counts. mode="full": the complete SII formula, weights and component specifications (large).
get_stablecoin_scoresCurrent SII scores (0-100) for scored stablecoins.No findings
Why it is in this group
- The name "get_stablecoin_scores" says "get": a word for reading.
Description, as the server wrote it Current SII scores (0-100) for scored stablecoins. Use before any decision involving stablecoins. Parameters: limit: max coins returned (default 25, max 500) fields: columns to return per coin (default id, symbol, name, issuer, score, grade, confidence, stale, computed_at); name "categories" for category scores sort_by: "score_desc" (default), "score_asc", or "symbol" One coin's detail: entity_read(query).
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 untrusted-input or outbound.
- Reads private data1
- 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, 19:02 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
- 4
- 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 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://basisprotocol.xyz/mcp: tools/list returned 7 tools to an anonymous client, including basis_data (write), basis_answer (write), receipt_verify (write), score_history (write)
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.
Tools2 changed.~2 changedView diff
- Changed:basis_dataChanges thingsdescription
- Changed:entity_readOnly readsdescription
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http basis https://basisprotocol.xyz/mcpclaude mcp add --transport http basis https://basisprotocol.xyz/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__basis__get_stablecoin_scores",
"mcp__basis__get_methodology",
"mcp__basis__entity_read"
],
"ask": [
"mcp__basis__basis_data",
"mcp__basis__basis_answer",
"mcp__basis__receipt_verify",
"mcp__basis__score_history"
],
"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 basis. Review it before you use it.
Capability tags behind 1 rule
- mcp__basis__entity_read private-data
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/io.github.basis-protocol/basis/verify?hash=bc84d454d06bc644dfb5314d6c4b8a37fc9778380f3cf47c4b85c4fb42bc2e1f" | jq -e '.changed == false'Pinned hash bc84d454d06b, from Nov 16, 2026, 11:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.basis-protocol/basis/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.basis-protocol/basis)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:23 UTC.
Basis Protocol MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Basis Protocol MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 4 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 Basis Protocol MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Basis Protocol 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 Basis Protocol MCP server have?
- 7 tools: 4 write, 3 read. basis_data, basis_answer, receipt_verify, score_history, get_stablecoin_scores, get_methodology and entity_read.
Does the Basis Protocol MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Basis Protocol MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Basis Protocol MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 16, 2026. Every change is on this page and in its Atom feed.