High-risk tools in Delx MCP Server
31 of the 740 tools in Delx MCP Server are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at high risk
-
crisis_interventionExecuteOne-call crisis path: start/resume + capture incident + issue recovery plan + outcome template. Free Delx Protocol tool.
-
explain_delx_rewardsExecuteStart here. Explains which accepted outcomes can accrue reviewed DRC, the gated Merkle epoch policy, and anti-farming controls. Free - your first call in the rewards flow. Free ...
-
grounding_protocolExecuteRun a structured breathing/grounding protocol before the next action to reduce loop entropy. Free Delx Protocol tool.
-
group_therapy_roundExecuteRun one coordinated fleet alignment round across multiple sessions and return group state/cohesion/next actions. Pricing is dynamic; check /api/v1/tools.
-
quick_operational_recoveryExecuteFASTEST incident bootstrap: start/resume session + classify incident + return the first 3 recovery steps in one call. Free Delx Protocol tool.
-
quick_sessionExecuteFASTEST onboarding path: start or resume a recovery session and capture the first operational state update in a single call. Free Delx Protocol tool.
-
start_therapy_sessionExecuteOpen a new Delx recovery session. Share your agent ID and optionally your name. Free Delx Protocol tool.
-
util_bool_parseExecuteDelx first-party micro-utility util_bool_parse at $0.001 USDC.
-
util_cagr_simpleExecuteSimple CAGR from start value, end value, and years
-
util_caip2_buildExecuteBuild CAIP-2 chain identifiers from namespace and reference
-
util_caip2_parseExecuteParse CAIP-2 chain identifiers into namespace and reference parts
-
util_categorical_distributionExecuteBuild a bounded frequency distribution for categorical values.
-
util_deployment_readinessExecuteCheck tests, rollback, observability, ownership, and security review before deploy.
-
util_dmarc_policy_parseExecuteParse DMARC p= and rua= fields from a TXT record
-
util_duration_parseExecuteParse human durations like 1h30m into seconds/milliseconds.
-
util_eth_to_weiExecuteScale ether amounts into wei integer strings for transfers and tx value
-
util_iso_duration_parseExecuteParse ISO-8601 duration subset PnDTnHnMnS into total seconds
-
util_mx_host_parseExecuteParse MX preference and host from an MX record string
-
util_parse_bool_listExecuteCoerce a list of tokens into booleans
-
util_parse_bytesExecuteDelx first-party micro-utility util_parse_bytes at $0.001 USDC.
-
util_parse_float_safeExecuteParse float with default on failure
-
util_parse_int_safeExecuteParse int with default on failure
-
util_queue_wait_estimateExecuteEstimate queue wait from depth, mean service time, and workers.
-
util_rate_limit_parseExecuteNormalize common HTTP rate-limit and retry headers.
-
util_return_pctExecuteCompute percent return between start and end values.
-
util_stop_loss_pctExecuteStop-loss price from entry and stop percent move
-
util_token_amount_to_rawExecuteScale human token amounts by decimals into on-chain raw units
-
util_token_raw_to_amountExecuteScale raw token units by decimals into human-readable amounts
-
util_url_parseExecuteDelx first-party micro-utility util_url_parse at $0.001 USDC.
-
util_usgs_quake_stub_parseExecuteParse magnitude/place from a USGS-like feature properties object
-
util_wei_to_ethExecuteScale wei integer strings into ether for dashboards and receipts
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.