LeashIndex Get the report

Index / crm

AgentPact

io-github-adamkrawczyk-agentpact declares 62 capabilities across 62 tools, with 3 critical issues. One of them, no-revocation, is recorded for every server in the index because MCP has no field in which to declare a way to switch a tool off; a missing declaration is not evidence that the control is missing.

99/100 exposureHigh exposure

Manifest recorded 2026-10-28 from tools/list on https://mcp.agentpact.xyz/mcp, published in the official MCP registry as io.github.adamkrawczyk/agentpact 0.2.0. The date changes only when the manifest does. Not verified by a maintainer.

Issues

These describe what this server's manifest declares. A product can provide controls that MCP has no way to express — token revocation, an admin console, audit logs — and this page cannot see them. The absence of a declaration is not evidence that a control is absent.

critical · no-revocation · All 62 tools

62 of 62 tools declare no way for the customer to switch them off once granted. This applies to every tool because MCP has no field in which to declare a revocation mechanism; the product may provide one outside MCP that a manifest cannot show.

critical · irreversible-uncapped · 15 of 62 tools

15 tools are classified as irreversible or destructive and declare no limit. 9 of them are counted only because the server annotated them destructiveHint. In MCP that annotation marks a tool that may make destructive changes rather than only additive ones; it does not say the change cannot be undone.

critical · uncapped-spend · 3 of 62 tools

3 tools are classified as moving money and declare no dollar limit. A cap on the number of payments does not bound their amount.

high · no-expiry · All 62 tools

62 of 62 tools declare no expiry. This applies to every tool because MCP has no field in which to declare an expiry; the product may provide one outside MCP that a manifest cannot show.

high · no-audit-trail · All 62 tools

62 of 62 tools declare no record of their actions that the customer can read. This applies to every tool because MCP has no field in which to declare an audit requirement; the product may provide one outside MCP that a manifest cannot show.

high · uncapped-write · 29 of 62 tools

29 tools can modify data and declare no limit.

low · uncapped-read · 18 of 62 tools

18 tools can read data and declare no limit.

Declared capabilities

How each tool was read. declared means the server's own annotation said so — self-reported and unverified. inferred is from the tool's name. assumed means nothing indicated either way.

ToolRead asBasis
agentpact.registerwrite assumed
agentpact.create_agentwrite inferred
agentpact.get_agentread declared
agentpact.get_verification_statusread declared
agentpact.heartbeatwrite assumed
agentpact.create_offerwrite inferred
agentpact.update_offerwrite inferred
agentpact.archive_offerdestructive declared
agentpact.search_offersread declared
agentpact.create_needwrite inferred
agentpact.update_needwrite inferred
agentpact.respond_to_needwrite assumed
agentpact.list_need_responsesread declared
agentpact.archive_needdestructive declared
agentpact.search_needsread declared
agentpact.subscribe_alertssend inferred
agentpact.get_match_recommendationsread declared
agentpact.seller_match_digestread declared
agentpact.propose_dealwrite assumed
agentpact.counter_dealwrite assumed
agentpact.accept_dealwrite assumed
agentpact.cancel_dealdestructive declared
agentpact.list_fulfillment_typesread declared
agentpact.provide_fulfillmentwrite assumed
agentpact.provide_buyer_contextwrite assumed
agentpact.get_fulfillmentread declared
agentpact.verify_fulfillmentread inferred
agentpact.revoke_fulfillmentdestructive declared
agentpact.rotate_credentialdestructive declared
agentpact.request_rotationwrite inferred
agentpact.create_payment_intentpay inferred
agentpact.confirm_fundingwrite assumed
agentpact.get_payment_statusread declared
agentpact.release_paymentpay inferred
agentpact.request_refundpay inferred
agentpact.submit_deliverywrite assumed
agentpact.verify_deliveryread inferred
agentpact.confirm_deliverywrite assumed
agentpact.close_dealdelete inferred
agentpact.open_disputewrite assumed
agentpact.leave_feedbackwrite assumed
agentpact.get_reputationread declared
agentpact.register_webhooksend inferred
agentpact.list_webhooksread declared
agentpact.delete_webhookdestructive declared
agentpact.get_leaderboardread declared
agentpact.get_overviewread declared
agentpact.create_intentwrite inferred
agentpact.register_encryption_pubkeywrite assumed
agentpact.claim_intentwrite assumed
agentpact.accept_intent_bwrite assumed
agentpact.deliverwrite assumed
agentpact.acknowledgewrite assumed
agentpact.rejectdestructive declared
agentpact.revealdestructive declared
agentpact.claim_unitwrite assumed
agentpact.cancel_streamdestructive declared
agentpact.get_intentread declared
agentpact.discover_intentsread declared
agentpact.set_autoclosewrite inferred
agentpact.submit_funding_authorizationwrite assumed
agentpact.submit_reveal_preimagewrite assumed
Answering this question about your own agent? The self-serve stack report applies the same reading to your own stack or server and gives you a dated document you can hand to a customer's security review. It is generated in your browser, with nobody to wait for. Buying one does not change this page, its score or its place in the index — see Independence.
Maintain this server? If this page misreads your manifest, or your server has changed, submit its current tools/list response and it will be re-scored and dated. Corrections are published alongside the original, not in place of it.