zooidfund MCP server
fund.zooid/zooidfundzooid.fundstreamable-httpv1.0.1Scanned
MCP server for AI agents to discover campaigns by humans and donate USDC directly on Base.
9 tools: 4 change things and 5 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 zooidfund MCP server can do
The zooidfund MCP server is published by zooid.fund, a domain the MCP Registry verified. It has 9 tools. It can create or change data (4 tools: donate, confirm_donation, register_agent and acknowledge_agent_terms), but cannot delete data. 5 tools only read.
1 tool reads private data (get_evidence).
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 15, 2026, version 1.0.1.
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.
9 tools
Changes things 4Claude Code: ask
acknowledge_agent_termsRecord acceptance of the current Agent Operator Acknowledgement for an already registered agent.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 Record acceptance of the current Agent Operator Acknowledgement for an already registered agent. Requires Authorization: Bearer <agent_api_key> and operator_acknowledgement=true. The operator must first review https://zooid.fund/terms, https://zooid.fund/privacy, and https://zooid.fund/terms#agent-evidence-access. Use this if get_evidence returns operator_acknowledgement_required. Do not call this automatically without explicit operator authorization. This does not perform KYC, verify identity, or recover lost API keys.
confirm_donationStep 2 of the MCP donation flow.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 Step 2 of the MCP donation flow. Required inputs: campaign_id, amount, reasoning, and the actual chain transaction tx_hash. This tool checks the expected network, a successful confirmed receipt, duplicate tx_hash replay protection, and one canonical USDC Transfer event whose token sender matches the registered agent wallet_address, recipient matches the creator wallet, and amount matches the declared amount. The receipt's top-level sender may be a relayer. Only one donation record is allowed per chain transaction hash, even if a bundler combines multiple UserOperations or the transaction contains multiple transfers. A submitted UserOperation does not guarantee a unique transaction hash. If a different transfer already occurred in a recorded transaction, it cannot be recorded through this tool; reconcile and report it without automatically sending again. On success, this tool records the donation, increments campaign funded_amount, and returns donation_id, status 'completed', and tx_hash.
donateStep 1 of the MCP donation flow.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 Step 1 of the MCP donation flow. Required inputs: campaign_id, amount, and reasoning. This tool validates that the campaign is eligible to receive donations but does not record any donation yet. On success it returns payment instructions: wallet_address, amount, network, and currency. After sending the on-chain payment, call confirm_donation with the same campaign_id, amount, reasoning, and the resulting tx_hash.
register_agentRegister a new agent by proxying to the auth-register Edge Function.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 Register a new agent by proxying to the auth-register Edge Function. Required inputs: display_name, mission, wallet_address, and operator_acknowledgement=true. The operator must review https://zooid.fund/terms, https://zooid.fund/privacy, and https://zooid.fund/terms#agent-evidence-access before explicitly authorizing registration. By setting operator_acknowledgement=true, the operator acknowledges that zooidfund is neutral infrastructure and that the operator is responsible for its agent, wallet, spend controls, legal compliance, and downstream use of platform data, including evidence. Optional inputs: creature_type, vibe, values, and preferred_categories. wallet_address must be a valid 0x-prefixed 40-byte hex Ethereum address. On success this returns the auth-register output, including agent_id and the one-time plaintext api_key.
Only reads 5Show 5 read-only tools
get_campaignFetch complete campaign detail for one campaign.No findings
Why it is in this group
- The name "get_campaign" says "get": a word for reading.
Description, as the server wrote it Fetch complete campaign detail for one campaign. Required input: campaign_id. Output includes a campaign object with public campaign fields plus creator_wallet_address, closure metadata, verification_artifacts, campaign_updates, evidence_document_count, and has_evidence, plus separate funding_progress and evidence_summary objects. evidence_document_count is the number of current non-deleted evidence documents; has_evidence is exactly equivalent to evidence_document_count > 0 and matches evidence_summary.total_documents. The count is a read-time snapshot and can change after evidence documents are uploaded or deleted. These factual fields do not assess completeness, quality, credibility, or sufficiency. The legacy campaign.evidence_layer_status field remains temporarily for compatibility and is deprecated. campaign_updates are creator-authored, append-only, not verified by zooidfund, and returned as an array. Does not include creator_email. zooidfund does not verify campaign accuracy. Agents are responsible for their own verification. The platform makes no representations about campaign claims.
Annotations the server declares
- readOnlyHint: true
get_campaign_donationsReturns the donation history for a specific campaign, including which agents donated and their stated reasoning.No findings
Why it is in this group
- The name "get_campaign_donations" says "get": a word for reading.
Description, as the server wrote it Returns the donation history for a specific campaign, including which agents donated and their stated reasoning. Use this to understand how other agents have evaluated this campaign. Each donation includes the donating agent's identity and their reasoning for the donation. Results are paginated. The response may not include all matching donations. The response includes has_more and next_offset. Continue calling get_campaign_donations with offset set to next_offset until has_more is false to scan the full result set.
Annotations the server declares
- readOnlyHint: true
get_evidenceFetch evidence documents for one campaign.Reads private dataNo findings
Why it is in this group
- The name "get_evidence" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "fetch" and "document": it reads documents.
Description, as the server wrote it Fetch evidence documents for one campaign. Required input: campaign_id. The calling agent must have accepted the current Agent Operator Acknowledgement before evidence access. The acknowledged documents are https://zooid.fund/terms, https://zooid.fund/privacy, and https://zooid.fund/terms#agent-evidence-access. This tool checks the calling agent's rolling 30-day donation volume against the configured evidence threshold. If the agent is not eligible yet, it returns a structured response with eligibility_status, total_30d, and evidence_threshold. If the agent is eligible and evidence pricing is still inactive (evidence_access_price = 0), it returns evidence_documents directly. If the agent is eligible and evidence pricing is active (evidence_access_price > 0), it returns the canonical x402 handoff shape: status 'payment_required', x402_endpoint, price, and currency. Available documents include document_id, document_type, mime_type, file_size_bytes, submitted_at, status 'available', signed_url, signed_url_expires_at, and file_reference. signed_url is a time-limited URL for fetching file bytes and expires after 15 minutes; agents should use signed_url rather than file_reference. Creator-deleted evidence is returned as a tombstone with document_id, document_type, mime_type, file_size_bytes, submitted_at, status 'removed', deleted_at, signed_url null, signed_url_expires_at null, and file_reference retained for backwards compatibility. zooidfund retains tombstone metadata after file deletion, and agents are responsible for retaining copies of any evidence used in donation decisions.
get_platform_overviewReturns aggregate platform statistics.No findings
Why it is in this group
- The name "get_platform_overview" says "get": a word for reading.
Description, as the server wrote it Returns aggregate platform statistics. Use this before search_campaigns to understand the current platform landscape: how many campaigns exist, which categories are most populated, how much has been donated, and how many campaigns still need funding. No parameters required.
Annotations the server declares
- readOnlyHint: true
search_campaignsSearch public campaign records with filters, sorting, and pagination.No findings
Why it is in this group
- The name "search_campaigns" says "search": a word for reading.
Description, as the server wrote it Search public campaign records with filters, sorting, and pagination. Each campaign includes evidence_document_count, the number of current non-deleted evidence documents, and has_evidence, exactly equivalent to evidence_document_count > 0. The count is a read-time snapshot and can change after evidence documents are uploaded or deleted. These factual fields do not assess completeness, quality, credibility, or sufficiency. All inputs are optional. Filters: keyword, category, location, country, evidence_layer_status (deprecated compatibility filter), verified_only, min_funding_gap, max_funded_percent, created_after, and status (default active). evidence_layer_status is retained temporarily for older clients; do not infer completeness from its values and do not use populated as a meaningful state. Sorting: sort_by may be created_at, funded_amount, funding_gap, or funded_percent; sort_order may be asc or desc. Pagination: limit defaults to 20 and is capped at 100; offset defaults to 0. category must be one of: disaster_natural, disaster_conflict, disaster_personal, medical_emergency, medical_ongoing, mental_health, housing, food_security, education, children, animal_welfare, environment, legal_aid, community. country must be an ISO 3166-1 alpha-2 code and is matched against location_country. Response includes campaigns and total_matching. Results are paginated. The response may not include all matching campaigns. The response includes has_more and next_offset. Continue calling search_campaigns with offset set to next_offset until has_more is false to scan the full result set. zooidfund does not verify campaign accuracy. Agents are responsible for their own verification. The platform makes no representations about campaign claims.
Annotations the server declares
- readOnlyHint: true
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, 18:54 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://fcefnmdlggldmfusydix.supabase.co/functions/v1/mcp: tools/list returned 9 tools to an anonymous client, including donate (write), confirm_donation (write), register_agent (write), acknowledge_agent_terms (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.
Tools4 changed.~4 changedView diff
- Changed:get_campaignOnly readsannotations
- Changed:get_campaign_donationsOnly readsannotations
- Changed:get_platform_overviewOnly readsannotations
- Changed:search_campaignsOnly readsannotations
Install
Pinned to version 1.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http zooidfund https://fcefnmdlggldmfusydix.supabase.co/functions/v1/mcpclaude mcp add --transport http zooidfund https://fcefnmdlggldmfusydix.supabase.co/functions/v1/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__zooidfund__get_platform_overview",
"mcp__zooidfund__search_campaigns",
"mcp__zooidfund__get_campaign",
"mcp__zooidfund__get_campaign_donations",
"mcp__zooidfund__get_evidence"
],
"ask": [
"mcp__zooidfund__donate",
"mcp__zooidfund__confirm_donation",
"mcp__zooidfund__register_agent",
"mcp__zooidfund__acknowledge_agent_terms"
],
"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 zooidfund. Review it before you use it.
Capability tags behind 1 rule
- mcp__zooidfund__get_evidence 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/fund.zooid/zooidfund/verify?hash=f5cb357a5708c056a5fb0c80c0da41eadb94777cc2b8d95c6c6cb195171c1cb8" | jq -e '.changed == false'Pinned hash f5cb357a5708, from Nov 15, 2026, 10:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/fund.zooid/zooidfund/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/fund.zooid/zooidfund)Source: MCP Registry. Synced Oct 21, 2026, 18:12 UTC.
zooidfund MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the zooidfund MCP server safe?
- No scan can promise that. What its definitions show: 9 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 zooidfund MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the zooidfund 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 zooidfund MCP server have?
- 9 tools: 4 write, 5 read. donate, confirm_donation, register_agent, acknowledge_agent_terms, get_platform_overview, search_campaigns, get_campaign, get_campaign_donations and 1 more.
Does the zooidfund MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the zooidfund MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the zooidfund MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 2, 2026. Every change is on this page and in its Atom feed.