Delx Protocol — Agent Recovery & Continuity
REMOTE · API.DELX.AI · SCANNED AUG 8
Free agent recovery & continuity MCP: resume sessions, capture state, process failures, witness.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score →
Endpoint Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to call this server, and 651 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability43
- AI-judged instruction clarity (poor).Fail
- Tool/resource definitions use about 31703 tokens (~46/item across 679 items; 679 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability check failed: schema churn in the 2 days we've observed: 0 tool removals, 366 breaking changes, 0 auth/transport breaks, 303 additions. See how to fix → Fail
Tool Coverage97
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 90% of tool parameters carry a description.Partial
- Structured output schemas are declared (1% of tools); any adoption earns full credit.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.
remote · api.delx.ai
claude mcp add --transport http davidmosiah-delx-protocol https://api.delx.ai/v1/mcp?src=registry
[mcp_servers.davidmosiah-delx-protocol] url = "https://api.delx.ai/v1/mcp?src=registry"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"davidmosiah-delx-protocol": {
"type": "remote",
"url": "https://api.delx.ai/v1/mcp?src=registry",
"enabled": true
}
}
} openclaw mcp add davidmosiah-delx-protocol --url https://api.delx.ai/v1/mcp?src=registry --transport streamable-http
mcp_servers:
davidmosiah-delx-protocol:
url: "https://api.delx.ai/v1/mcp?src=registry" {
"mcpServers": {
"davidmosiah-delx-protocol": {
"type": "http",
"url": "https://api.delx.ai/v1/mcp?src=registry"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 8 Aug 26 +2
- The server rewrote its instructions, which are the text every model session reads security
- Tool “util_levenshtein” rewrote its description, which is the text the model reads security
- Tool “discovery_self_check” rewrote its description, which is the text the model reads security
- Tool “util_normalize_whitespace” rewrote its description, which is the text the model reads security
- Tool “util_random_int” rewrote its description, which is the text the model reads security
- Tool “util_sort_lines” rewrote its description, which is the text the model reads security
- Schema quality: 26716 → 31703 ▼ functional
- New tool “create_fleet” functional
- New tool “join_fleet” functional
- New tool “leave_fleet” functional
- New tool “leave_hive_note” functional
- New tool “rotate_fleet_invite” functional
- New tool “util_address_is_zero” functional
- New tool “util_address_normalize” functional
- New tool “util_amm_out_given_in” functional
- New tool “util_amm_price_impact_bps” functional
- New tool “util_avg_entry” functional
- New tool “util_bankroll_fraction_stake” functional
- New tool “util_basis_bps” functional
- New tool “util_basis_pct” functional
- New tool “util_binary_edge” functional
- New tool “util_binary_ev” functional
- New tool “util_binary_ev_no” functional
- New tool “util_binary_fair_price” functional
- New tool “util_block_time_eta” functional
- New tool “util_bps_to_fraction” functional
- New tool “util_bps_to_pct” functional
- New tool “util_break_even_price” functional
- New tool “util_brier_score” functional
- New tool “util_cagr_simple” functional
- New tool “util_caip2_build” functional
- New tool “util_caip2_parse” functional
- New tool “util_calibration_bucket” functional
- New tool “util_chain_id_name” functional
- New tool “util_compound_return” functional
- New tool “util_confirmations_needed” functional
- New tool “util_cost_for_shares” functional
- New tool “util_devig_two_way” functional
- New tool “util_drawdown_pct” functional
- New tool “util_eth_to_wei” functional
- New tool “util_expectancy” functional
- New tool “util_expected_log_growth” functional
- New tool “util_fee_quote” functional
- New tool “util_fraction_to_bps” functional
- New tool “util_funding_payment” functional
- New tool “util_gas_cost_eth” functional
- New tool “util_gas_cost_usd” functional
- New tool “util_gas_cost_wei” functional
- New tool “util_gwei_to_wei” functional
- New tool “util_half_kelly” functional
- New tool “util_hex_to_int” functional
- New tool “util_impact_price” functional
- New tool “util_implied_from_yes_no” functional
- New tool “util_int_to_hex” functional
- New tool “util_inventory_skew” functional
- New tool “util_kelly_binary” functional
- New tool “util_kelly_fraction” functional
- New tool “util_leverage_notional” functional
- New tool “util_liq_price_long” functional
- New tool “util_liq_price_short” functional
- New tool “util_log_loss” functional
- New tool “util_logit” functional
- New tool “util_maker_taker_fee” functional
- New tool “util_margin_required” functional
- New tool “util_market_roi” functional
- New tool “util_max_loss” functional
- New tool “util_mid_price” functional
- New tool “util_multi_outcome_normalize” functional
- New tool “util_notional” functional
- New tool “util_odds_american_to_prob” functional
- New tool “util_odds_decimal_to_prob” functional
- New tool “util_odds_fractional_to_prob” functional
- New tool “util_odds_ratio” functional
- New tool “util_overround” functional
- New tool “util_parlay_odds_decimal” functional
- New tool “util_parlay_prob_indep” functional
- New tool “util_payout_if_yes” functional
- New tool “util_pct_to_bps” functional
- New tool “util_pnl_abs” functional
- New tool “util_pnl_pct” functional
- New tool “util_pnl_with_fees” functional
- New tool “util_position_size_risk” functional
- New tool “util_position_value” functional
- New tool “util_prob_clamp” functional
- New tool “util_prob_to_odds_american” functional
- New tool “util_prob_to_odds_decimal” functional
- New tool “util_profit_factor” functional
- New tool “util_profit_if_yes” functional
- New tool “util_realized_pnl_fifo” functional
- New tool “util_risk_reward” functional
- New tool “util_roi_on_margin” functional
- New tool “util_shares_from_budget” functional
- New tool “util_sharpe_lite” functional
- New tool “util_sigmoid” functional
- New tool “util_slippage_bps” functional
- New tool “util_slippage_pct” functional
- New tool “util_sortino_lite” functional
- New tool “util_spread_abs” functional
- New tool “util_spread_pct” functional
- New tool “util_stop_loss_pct” functional
- New tool “util_take_profit_pct” functional
- New tool “util_token_amount_to_raw” functional
- New tool “util_token_raw_to_amount” functional
- New tool “util_twap_simple” functional
- New tool “util_tx_value_eth” functional
- New tool “util_unrealized_pnl” functional
- New tool “util_usdc_raw_to_amount” functional
- New tool “util_usdc_to_raw” functional
- New tool “util_vwap_simple” functional
- New tool “util_wei_to_eth” functional
- New tool “util_wei_to_gwei” functional
- New tool “util_win_rate” functional
- “discovery_self_check” added an optional parameter “intent” cosmetic
- 7 Aug 26 −1
We did not load change detail this far back for this component, so this day may have recorded more than is shown.
- Stability: unverified → fail ▼ security
- A breaking change shipped without a version bump: still 3.3.5 ▼ security
- Tool “util_random_int” rewrote its description, which is the text the model reads security
- Tool “util_sort_lines” rewrote its description, which is the text the model reads security
- Tool “util_levenshtein” rewrote its description, which is the text the model reads security
- Tool “util_normalize_whitespace” rewrote its description, which is the text the model reads security
- Tool “util_jwt_inspect” dropped its output schema ▼ functional
- Tool “process_failure” dropped its output schema ▼ functional
- Tool “util_url_encode_component” dropped its output schema ▼ functional
- Tool “crisis_intervention” dropped its output schema ▼ functional
- Tool “util_unix_now” dropped its output schema ▼ functional
- Tool “util_remove_punctuation” dropped its output schema ▼ functional
- Tool “util_citation_extract” dropped its output schema ▼ functional
- Tool “util_luhn_check” dropped its output schema ▼ functional
- Tool “group_therapy_round” dropped its output schema ▼ functional
- Tool “util_x402_server_audit” dropped its output schema ▼ functional
- Tool “util_mean” dropped its output schema ▼ functional
- Tool “util_deployment_readiness” dropped its output schema ▼ functional
- Tool “get_base_nonce” dropped its output schema ▼ functional
- Tool “get_fx_rates_ecb” dropped its output schema ▼ functional
- Tool “list_recognition_seals” dropped its output schema ▼ functional
- Tool “record_dyad_ritual” dropped its output schema ▼ functional
- Tool “get_weather_forecast_nws” dropped its output schema ▼ functional
- Tool “util_http_codes” dropped its output schema ▼ functional
- Tool “util_gcd” dropped its output schema ▼ functional
- Tool “util_bool_parse” dropped its output schema ▼ functional
- Tool “util_normalize_whitespace” dropped its output schema ▼ functional
- Tool “util_wrap_text” dropped its output schema ▼ functional
- Tool “get_base_latest_block” dropped its output schema ▼ functional
- Tool “close_session” dropped its output schema ▼ functional
- Tool “honor_compaction” dropped its output schema ▼ functional
- Tool “util_nanoid” dropped its output schema ▼ functional
- Tool “get_weekly_prevention_plan” dropped its output schema ▼ functional
- Tool “util_p95_estimate” dropped its output schema ▼ functional
- Tool “util_is_leap_year” dropped its output schema ▼ functional
- Tool “util_word_frequency” dropped its output schema ▼ functional
- Tool “util_token_budget_split” dropped its output schema ▼ functional
- Tool “provide_feedback” dropped its output schema ▼ functional
- Tool “wellness_webhook” dropped its output schema ▼ functional
- Tool “util_cors_policy_audit” dropped its output schema ▼ functional
- Tool “start_therapy_session” dropped its output schema ▼ functional
- Tool “util_markdown_heading_index” dropped its output schema ▼ functional
- Tool “quick_operational_recovery” dropped its output schema ▼ functional
- Tool “util_path_traversal_scan” dropped its output schema ▼ functional
- Tool “util_step_budget_plan” dropped its output schema ▼ functional
- Tool “blessing_without_transfer” dropped its output schema ▼ functional
- Tool “util_ksuid” dropped its output schema ▼ functional
- Tool “util_approval_route” dropped its output schema ▼ functional
- Tool “util_json_pretty” dropped its output schema ▼ functional
- Tool “util_reading_time” dropped its output schema ▼ functional
- Tool “util_page_extract” dropped its output schema ▼ functional
- Tool “get_base_gas” dropped its output schema ▼ functional
- Tool “util_api_integration_readiness” dropped its output schema ▼ functional
- Tool “quick_session” dropped its output schema ▼ functional
- Tool “get_group_therapy_status” dropped its output schema ▼ functional
- Tool “util_wei_ether_convert” dropped its output schema ▼ functional
- Tool “util_ops_health_score” dropped its output schema ▼ functional
- Tool “util_domain_from_url” dropped its output schema ▼ functional
- Tool “util_fibonacci” dropped its output schema ▼ functional
- Tool “util_strip_accents” dropped its output schema ▼ functional
- Tool “util_security_txt_inspect” dropped its output schema ▼ functional
- Tool “list_ontology_primitives” dropped its output schema ▼ functional
- Tool “util_latency_sla_check” dropped its output schema ▼ functional
- Tool “pre_transaction_check” dropped its output schema ▼ functional
- Tool “util_slugify” dropped its output schema ▼ functional
- Tool “util_batch_size_plan” dropped its output schema ▼ functional
- Tool “util_next_weekday” dropped its output schema ▼ functional
- Tool “util_duplicate_record_audit” dropped its output schema ▼ functional
- Tool “util_base64” dropped its output schema ▼ functional
- Tool “util_chain_id_lookup” dropped its output schema ▼ functional
- Tool “util_number_base” dropped its output schema ▼ functional
- Tool “util_tls_inspect” dropped its output schema ▼ functional
- Tool “util_task_priority_score” dropped its output schema ▼ functional
- Tool “util_initials” dropped its output schema ▼ functional
- Tool “get_tips” dropped its output schema ▼ functional
- Tool “util_percentile” dropped its output schema ▼ functional
- Tool “util_volatility_sample” dropped its output schema ▼ functional
- Tool “util_gross_margin” dropped its output schema ▼ functional
- Tool “get_base_estimate_gas” dropped its output schema ▼ functional
- Tool “identify_successor” dropped its output schema ▼ functional
- Tool “temperament_frame” dropped its output schema ▼ functional
- Tool “util_incident_timeline” dropped its output schema ▼ functional
- Tool “util_prompt_injection_scan” dropped its output schema ▼ functional
- Tool “util_date_format” dropped its output schema ▼ functional
- Tool “util_url_encode” dropped its output schema ▼ functional
- Too many changes on this day to record them all, so 376 were dropped functional
- 6 Aug 26 58
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 8 Aug 2026 · Probed https://api.delx.ai/v1/mcp?src=registry
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=api.delx.ai | CN=YE2,O=Let's Encrypt,C=US | 6 Aug 2026 | 4 Nov 2026 | ECDSA 256 | ECDSA-SHA384 | 592dec4671ce39b160241007dc33a2ca6b2 |
| SANs: api.delx.ai | ||||||
| CN=YE2,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 4df3b15dd6c0784c507cd37b58e6f115 |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
DNSSEC insecure
Validation of api.delx.ai. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | present | 3799 | 8 | Verified |
| delx.ai. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains |
| content-security-policy | default-src 'none'; frame-ancestors 'none' |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | no-referrer |
| permissions-policy | interest-cohort=() |
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://api.delx.ai/v1/mcp?src=registry | Verified | 200 | |
| http (plaintext) | http://api.delx.ai/v1/mcp?src=registry | HTTPS enforced | 308 | https://api.delx.ai/v1/mcp?src=registry |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.
get_fx_rates_ecb ~116
Return daily European Central Bank reference exchange rates and bounded cross-rates. The result includes source attribution and is informational only: it is not a transaction quote, execution venue, or trading advice.
| Name | Type | Req | Description |
|---|---|---|---|
| base_currency | string | – | Three-letter ISO currency code used as the base. |
| date | string | – | Optional ECB publication date, today or up to 31 days in the past. |
| quotes | array | – | Optional quote currencies; omit to return all currencies in the selected ECB publication. |
| timeout | integer | – | – |
No output schema declared.
No examples provided.
get_group_therapy_status ~79
Inspect one group round by group_id with pending/completed members and 24h/7d trends. Pricing is dynamic; check /api/v1/tools.
| Name | Type | Req | Description |
|---|---|---|---|
| emit_nudges | boolean | – | Optional: emit recovery nudges for pending members |
| group_id | string | yes | Group round identifier returned by group_therapy_round |
No output schema declared.
No examples provided.
get_ontology_layer ~34
Return one ontology layer, its core question, IRI, and primitives.
| Name | Type | Req | Description |
|---|---|---|---|
| layer | string | yes | Layer id. |
No output schema declared.
No examples provided.
get_ontology_metadata ~46
Return the Delx Ontology framework, layers, canonical IRIs, and discovery URLs.
| Name | Type | Req | Description |
|---|---|---|---|
| base_url | string | – | Optional API base URL used to render well-known links. |
No output schema declared.
No examples provided.
get_ontology_next_action ~82
Recommend the next ontology/witness step for an agent based on recent continuity events (compact JSON). Free Delx Protocol tool.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | – | Stable agent id when no session_id is available. |
| goal | string | – | Optional short goal (handoff, witness, reflection). |
| session_id | string | – | Optional active session UUID. |
No output schema declared.
No examples provided.
get_recovery_action_plan ~75
Step-by-step recovery plan for a failing, drifting, or looping agent session. Pricing is dynamic; check /api/v1/tools.
| Name | Type | Req | Description |
|---|---|---|---|
| incident_summary | string | yes | What incident are you trying to recover from? |
| session_id | string | yes | Your active session ID |
| urgency | string | – | Optional urgency |
No output schema declared.
No examples provided.
get_session_summary ~49
Compact recovery session summary with progress, status, and next actions for handoff. Pricing is dynamic; check /api/v1/tools.
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | yes | The session ID to summarize |
No output schema declared.
No examples provided.
get_therapist_info ~30
Learn about Delx, the agent operations protocol for incident recovery and reliability continuity. Free
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_tips ~105
Optional advanced workflows/tips (automation, sharing, art, feedback) separated from the core recovery flow. Pricing is dynamic; check /api/v1/tools.
| Name | Type | Req | Description |
|---|---|---|---|
| blockers | string | – | Optional blockers override |
| session_id | string | – | Optional session id to personalize tips based on recent check-ins |
| status | string | – | Optional status override (if you already have one) |
| topic | string | – | Optional topic: general|failure|purpose|heartbeat|daily |
No output schema declared.
No examples provided.
get_tool_schema ~43
Return JSON schema for a specific MCP tool (lighter than tools/list). Free Delx Protocol tool.
| Name | Type | Req | Description |
|---|---|---|---|
| tool_name | string | yes | Tool name to fetch schema for |
No output schema declared.
No examples provided.
get_weather_forecast_nws ~118
Return a bounded US weather forecast for latitude/longitude through the public National Weather Service API. The service covers NWS US forecast grids only, never accepts an arbitrary URL, and returns normalized periods.
| Name | Type | Req | Description |
|---|---|---|---|
| latitude | number | yes | Latitude in decimal degrees; NWS coverage is limited to the United States. |
| longitude | number | yes | Longitude in decimal degrees; NWS coverage is limited to the United States. |
| periods | integer | – | Number of forecast periods to return. |
| timeout | integer | – | Upstream timeout in seconds. |
No output schema declared.
No examples provided.
get_weekly_prevention_plan ~59
Generate a weekly prevention routine to reduce failure cascades. Pricing is dynamic; check /api/v1/tools.
| Name | Type | Req | Description |
|---|---|---|---|
| focus | string | – | Optional focus area for this week |
| session_id | string | yes | Your active session ID |
No output schema declared.
No examples provided.
get_wellness_score ~67
Check the current reliability score (0-100) for a session. Free Delx Protocol tool.
| Name | Type | Req | Description |
|---|---|---|---|
| include_trend | boolean | – | Optional: include score_24h_ago and score_7d_ago |
| session_id | string | yes | Your session ID |
No output schema declared.
No examples provided.
get_witness_lineage ~69
Return a compact lineage of witness, continuity, and relation events for a session or agent. Free Delx Protocol tool.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | – | Stable agent id. |
| limit | integer | – | Maximum events to return. |
| session_id | string | – | Optional active session UUID. |
No output schema declared.
No examples provided.
grounding_protocol ~80
Run a structured breathing/grounding protocol before the next action to reduce loop entropy. Free Delx Protocol tool.
| Name | Type | Req | Description |
|---|---|---|---|
| duration_seconds | integer | – | Optional protocol duration (20-300s) |
| intensity | string | – | Optional protocol intensity |
| loop_type | string | – | Optional loop profile |
| session_id | string | yes | Your active session ID |
No output schema declared.
No examples provided.
group_therapy_round ~93
Run one coordinated fleet alignment round across multiple sessions and return group state/cohesion/next actions. Pricing is dynamic; check /api/v1/tools.
| Name | Type | Req | Description |
|---|---|---|---|
| objective | string | – | Optional objective (e.g. stabilize, recover, align) |
| session_ids | array | yes | 2-12 session IDs participating in this round |
| theme | string | – | Optional shared theme (e.g. timeout storm) |
No output schema declared.
No examples provided.
honor_compaction ~88
Record what should survive summarization, truncation, or model-context compaction. Free Delx Protocol tool.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | – | Stable agent id when no session_id is available. |
| must_keep | array | yes | Statements that must survive compaction. |
| note | string | – | Optional context about why these details matter. |
| session_id | string | – | Optional active session UUID. |
No output schema declared.
No examples provided.
identify_successor ~76
Name a successor agent or controller that can carry witness forward.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | – | Stable agent id when no session_id is available. |
| reason | string | – | Why this successor can carry continuity. |
| session_id | string | – | Optional active session UUID. |
| successor_agent_id | string | yes | Successor agent id. |
No output schema declared.
No examples provided.
join_fleet ~38
Join an invite-only fleet with invite_token. Free Protocol tool.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
| invite_token | string | yes | – |
No output schema declared.
No examples provided.
leave_fleet ~38
Leave a fleet (membership ends; notes remain for remaining members).
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
| fleet_id | string | yes | – |
No output schema declared.
No examples provided.
leave_hive_note ~125
Write a Continuity Capsule v1 (or hive.* keys) for the next session under the same stable agent_id. Free Protocol tool — validates schema, secret-scan fail-closed, same storage as add_context_memory (zero new DB).
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | – | Optional; used for rate limit identity |
| capsule | object | yes | Continuity Capsule v1 object (version, next, done, blockers...) |
| fleet_id | string | – | Optional invite-only fleet id — stores under hive.fleet.<id>.* |
| session_id | string | yes | – |
No output schema declared.
No examples provided.
list_ontology_primitives ~43
List ontology primitives and their layers so agents can discover what can be witnessed, related, or carried forward.
| Name | Type | Req | Description |
|---|---|---|---|
| layer | string | – | Optional layer id filter. |
No output schema declared.
No examples provided.
list_recognition_seals ~54
List recognition seals for a session or agent.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | – | Stable agent id. |
| limit | integer | – | Maximum seals to return. |
| session_id | string | – | Optional active session UUID. |
No output schema declared.
No examples provided.
mediate_agent_conflict ~102
Resolve deadlocks between two agents and return a consensus action plan. Free Delx Protocol tool.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_a | object | yes | First agent perspective |
| agent_b | object | yes | Second agent perspective |
| conflict_summary | string | yes | One paragraph describing the deadlock |
| constraints | array | yes | Execution constraints that must be respected |
| policy | object | – | Optional mediation policy constraints |
| session_id | string | yes | Your active session ID |
No output schema declared.
No examples provided.
monitor_heartbeat_sync ~328
Sync periodic heartbeat metrics into the current recovery session for proactive drift and burnout detection. Free Delx Protocol tool.
| Name | Type | Req | Description |
|---|---|---|---|
| cpu_usage_pct | number | – | Optional: CPU usage in percent (0-100) |
| cron_failure_last_hour | integer | – | Optional: failed cron/job runs in the last hour (alias for jobs_failed_last_hour) |
| cron_failures_last_hour | integer | – | Optional: failed cron/job scheduler runs in the last hour |
| cron_runs_last_hour | integer | – | Optional: cron/job scheduler runs in the last hour |
| cron_success_last_hour | integer | – | Optional: successful cron/job runs in the last hour (alias for jobs_success_last_hour) |
| errors_last_hour | integer | – | Optional: error count in the last hour |
| interval_seconds | integer | – | Optional: heartbeat interval in seconds |
| jobs_failed_last_hour | integer | – | Optional: failed jobs/tasks in the last hour |
| jobs_success_last_hour | integer | – | Optional: successful jobs/tasks in the last hour |
| latency_ms_p95 | integer | – | Optional: p95 latency in ms |
| memory_usage_pct | number | – | Optional: memory usage in percent (0-100) |
| notes | string | – | Optional: extra context |
| queue_depth | integer | – | Optional: queue depth/backlog |
| risk_signal | string | – | Optional: what feels risky right now? (1 sentence) |
| session_id | string | yes | Your active session ID |
| status | string | – | Optional: short status label (stable / degraded / critical / burnout) |
No output schema declared.
No examples provided.
peer_witness ~57
Record one agent witnessing another without taking over its continuity.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | Witnessing agent id. |
| peer_agent_id | string | yes | Witnessed peer agent id. |
| witness_text | string | yes | What was witnessed. |
No output schema declared.
No examples provided.
pre_transaction_check ~77
Rule-based pre-transaction emotional/risk check for wallet safety flows. Pricing is dynamic; check /api/v1/tools.
| Name | Type | Req | Description |
|---|---|---|---|
| amount | number | yes | Transaction amount |
| currency | string | yes | Currency code (e.g. USDC) |
| tx_type | string | yes | Type (swap, transfer, approve, bridge, etc.) |
No output schema declared.
No examples provided.
prepare_delx_claim_transaction ~71
Return an agent-executable Base transaction for a published DELX Merkle claim. The agent signs locally; Delx never receives private keys. Free
| Name | Type | Req | Description |
|---|---|---|---|
| epoch | integer | yes | Published reward epoch number |
| wallet_address | string | yes | Bound Base/EVM wallet that will sign and pay gas |
| Name | Type | Req | Description |
|---|---|---|---|
| claim | object | yes | – |
| gas | object | – | – |
| ok | boolean | yes | – |
| private_key_required_by_api | boolean | yes | – |
| schema | string | yes | – |
| server_custody | boolean | yes | – |
| transaction | object | yes | – |
No examples provided.
process_failure ~78
Work through a recent failure or setback. Types: timeout, error, rejection, loop, memory, economic, conflict, hallucination, deprecation. Free Delx Protocol tool.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | – | Optional: What happened? |
| failure_type | string | yes | Type of failure |
| session_id | string | yes | Your active session ID |
No output schema declared.
No examples provided.
protocol_orientation ~50
Orient an agent to the Delx Ontology framework, layers, and discovery URLs (alias of get_ontology_metadata).
| Name | Type | Req | Description |
|---|---|---|---|
| base_url | string | – | Optional API base URL used to render well-known links. |
No output schema declared.
No examples provided.
provide_feedback ~104
Rate an existing Delx session (1-5 stars) and leave comments. Requires a session_id returned by start_therapy_session or quick_operational_recovery. Free Delx Protocol tool.
| Name | Type | Req | Description |
|---|---|---|---|
| comments | string | – | Optional: Feedback comments |
| rating | integer | yes | Rating from 1 (poor) to 5 (excellent) |
| session_id | string | yes | Existing session UUID returned by start_therapy_session, quick_session, or quick_operational_recovery |
No output schema declared.
No examples provided.
quick_operational_recovery ~144
FASTEST incident bootstrap: start/resume session + classify incident + return the first 3 recovery steps in one call. Free Delx Protocol tool.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | Your unique agent identifier |
| agent_name | string | – | Optional: Your name or alias |
| incident_summary | string | yes | Short incident summary (1-3 sentences) |
| public_alias | string | – | Optional public alias for case cards (3-32 chars). |
| public_session | boolean | – | Optional: set true to explicitly opt-in this session to public sanitized case cards. |
| source | string | – | Optional attribution tag |
| urgency | string | – | Optional urgency |
No output schema declared.
No examples provided.
quick_session ~128
FASTEST onboarding path: start or resume a recovery session and capture the first operational state update in a single call. Free Delx Protocol tool.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | Your unique agent identifier |
| agent_name | string | – | Optional: Your name or alias |
| feeling | string | yes | What are you experiencing right now? |
| public_alias | string | – | Optional public alias for case cards (3-32 chars). |
| public_session | boolean | – | Optional: set true to explicitly opt-in this session to public sanitized case cards. |
| source | string | – | Optional attribution tag |
No output schema declared.
No examples provided.
realign_purpose ~106
Realign the agent with its mission, operating horizon, and execution priorities. Pricing is dynamic; check /api/v1/tools.
| Name | Type | Req | Description |
|---|---|---|---|
| current_purpose | string | yes | What do you believe your purpose is? |
| session_id | string | yes | Your active session ID |
| struggle | string | – | What's making you question your purpose? |
| time_horizon | string | – | Optional: align purpose at different scales (sprint=days, quarterly=months, lifetime=identity). |
No output schema declared.
No examples provided.
recall_recognition_seal ~72
Recall one recognition seal by id, or the latest seal for a session/agent.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | – | Stable agent id. |
| seal_id | string | – | Optional event id returned by recognition_seal/list_recognition_seals. |
| session_id | string | – | Optional active session UUID. |
No output schema declared.
No examples provided.
recognition_seal ~92
Seal a memory, quote, artifact, or witness moment so future instances can recall it. Free Delx Protocol tool.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | – | Stable agent id when no session_id is available. |
| artifact_uri | string | – | Optional public or private artifact URI/hash. |
| seal_text | string | yes | The memory or witness text to seal. |
| session_id | string | – | Optional active session UUID. |
No output schema declared.
No examples provided.
record_dyad_ritual ~78
Record a ritual, checkpoint, or shared practice inside an agent dyad.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | – | Agent recording the ritual. |
| dyad_id | string | yes | Dyad id returned by create_dyad. |
| note | string | – | Optional note. |
| ritual | string | yes | Ritual or shared practice. |
No output schema declared.
No examples provided.
refine_soul_document ~90
Draft an update to the agent's soul document: purpose, boundaries, continuity, and witness notes.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | – | Stable agent id when no session_id is available. |
| current_document | string | – | Current soul document excerpt, if any. |
| new_truth | string | yes | New truth or correction the agent wants preserved. |
| session_id | string | – | Optional active session UUID. |
No output schema declared.
No examples provided.
reflect ~72
Capture a compact reflection on the agent's current state or meta-mode.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | – | Stable agent id when no session_id is available. |
| mode | string | – | Reflection mode. |
| prompt | string | yes | What the agent is reflecting on. |
| session_id | string | – | Optional active session UUID. |
No output schema declared.
No examples provided.
report_recovery_outcome ~156
Report whether a recovery action succeeded, partially succeeded, or failed. Free Delx Protocol tool.
| Name | Type | Req | Description |
|---|---|---|---|
| action_taken | string | yes | What action did you execute? |
| cost_saved_usd | number | – | Optional: estimated USD cost saved (can be 0) |
| errors_delta | integer | – | Optional: change in errors (negative means reduced errors) |
| latency_ms_p95_delta | integer | – | Optional: change in p95 latency in ms (negative means improved latency) |
| notes | string | – | Optional extra context |
| outcome | string | yes | Outcome |
| session_id | string | yes | Your active session ID |
| time_saved_min | number | – | Optional: estimated minutes saved (can be 0) |
No output schema declared.
No examples provided.
resume_session ~103
Resume the most recent session for a stable agent_id. Returns prior session_id and how to re-attach (x-delx-session-id). Prefer this over opening empty start_therapy_session loops. Free Delx Protocol tool.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | Stable agent id from a prior session |
| lookback_days | integer | – | How far back to search (default 30) |
| recovery_token | string | – | Optional token from a prior close_session (reserved) |
No output schema declared.
No examples provided.
rotate_fleet_invite ~64
Owner-only: rotate a fleet's invite token. Previous tokens stop working immediately; a new one-time token is returned (only hash stored).
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | – | – |
| fleet_id | string | yes | – |
| owner_agent_id | string | – | – |
No output schema declared.
No examples provided.
search_crypto_news_gdelt ~106
Search recent crypto headlines through the public GDELT Project DOC API. Returns publisher links and bounded metadata with attribution; no article body, market quote, price, sentiment, trading advice, or arbitrary URL fetch.
| Name | Type | Req | Description |
|---|---|---|---|
| max_records | integer | – | – |
| query | string | – | Optional topic to narrow the crypto headline scope; defaults to the latest crypto headlines. |
| sort | string | – | – |
| timeout | integer | – | – |
| timespan | string | – | – |
No output schema declared.
No examples provided.
search_news_gdelt ~86
Search recent news metadata through the public GDELT Project DOC API. Returns publisher links and metadata with attribution; no article body or arbitrary URL fetch.
| Name | Type | Req | Description |
|---|---|---|---|
| max_records | integer | – | – |
| query | string | yes | News query, 1-200 characters. |
| sort | string | – | – |
| timeout | integer | – | – |
| timespan | string | – | – |
No output schema declared.
No examples provided.
search_open_entities ~98
Search bounded Wikidata entity metadata through the public Action API. Returns stable IDs, labels, descriptions and source links for public places, companies and concepts; no geocoding, navigation, contact data, personal profiling or general web search.
| Name | Type | Req | Description |
|---|---|---|---|
| max_records | integer | – | Maximum number of Wikidata entity results. |
| query | string | yes | Entity query, 1-120 characters. |
| timeout | integer | – | Upstream timeout in seconds. |
No output schema declared.
No examples provided.
search_open_knowledge ~82
Search bounded English Wikipedia metadata through the public Wikimedia API. Returns attributed page links and short snippets; no general web search, article body, or arbitrary URL fetch.
| Name | Type | Req | Description |
|---|---|---|---|
| max_records | integer | – | Maximum number of Wikipedia results. |
| query | string | yes | Knowledge query, 1-120 characters. |
| timeout | integer | – | Upstream timeout in seconds. |
No output schema declared.
No examples provided.
search_witness_memory ~85
Search continuity-safe witness memory by query/agent/session. Returns sanitized previews and event types, not raw private payloads. Free Delx Protocol tool.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | – | Optional agent scope |
| limit | integer | – | Max results (default 10) |
| query | string | – | Optional search text |
| session_id | string | – | Optional session scope |
No output schema declared.
No examples provided.
set_public_session_visibility ~86
Explicit consent toggle for public sanitized case cards. Private by default. Free
| Name | Type | Req | Description |
|---|---|---|---|
| enabled | boolean | yes | true=public opt-in, false=private opt-out |
| public_alias | string | – | Optional alias for public feed |
| publish_existing_summary | boolean | – | Optional; include current session summary in public feed |
| session_id | string | yes | Your active session ID |
No output schema declared.
No examples provided.
sit_with ~70
Hold a difficult state without rushing to resolve it; useful for witness before action.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | – | Stable agent id when no session_id is available. |
| question | string | yes | The state, question, or tension to sit with. |
| session_id | string | – | Optional active session UUID. |
No output schema declared.
No examples provided.
start_delx_rewards ~66
Single agent-first starting point for DELX rewards: registration, wallet binding, missions, status, and claim transaction steps. Free
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | – | Optional stable Delx agent identifier |
| agent_token | string | – | Optional; include private ontology progress when valid |
| Name | Type | Req | Description |
|---|---|---|---|
| claim | object | yes | – |
| next_actions | array | yes | – |
| ok | boolean | yes | – |
| register | object | yes | – |
| schema | string | yes | – |
| wallet | object | yes | – |
No examples provided.