Agents Index

Did It Work?

OnlineNew

Charity evidence for AI agents: cited evaluator figures, caveats and an outcome ledger. Read-only.

Visit publisherConnectJSON

What it can do: 22 tools

  • decision_brief read-onlyCall this first for any donor question (where to give, is X any good, compare, top N, a doubt or a challenge). One call, one defensible answer: put the donor's question in their own words (question), optionally with a ca
  • recommend_charity read-onlyConviction-ranked orgs for one outcome family. Pass values_profile_id (preferred) and/or outcome. Returns values_filtering + exclusions[] with why-filtered reasons (never silent red-line drops). Does not mix units (ADR 0
  • list_charities read-onlyThe Did it work? charity list, filtered: the charities https://diditwork.org/charities/ shows for cause, evaluator (by), measure, follow-up and a word search, in the page's own order. Hide-only: filters never re-order, s
  • search_orgs read-onlyHeuristic search by cause, outcome family, or donor intent phrase. Prefer recommend_charity when the user wants ranked 'best for outcome' results. An empty result carries coverage (what we don't cover and what to do inst
  • get_org read-onlyFetch one organization / program / fund record by stable org_* id. Answers carry decision_brief: the charity's own donate_url (next_action), the evaluator's fund as a let-the-evaluator-choose alternative, the like-for-li
  • compare_charities read-onlySide-by-side claims, recommendation tiers, and trust for two or more org_* ids. When the charities are measured in different outcome units (for example wellbeing in WELLBYs versus lives saved), units_differ.sentence says
  • verdict_chain read-onlyThe verdict chain for one charity, link by link (L0 Defined to L7 Checked), read out only from data we already hold: the evidence-gap ledger, our outcome ledger, the evaluator figures we hold and the verdict procedure (h
  • estimate_impact read-onlyModeled expected outcomes from verified org claims scaled by gift_usd. Always modeled:true and guaranteed:false. Never invents CE; returns insufficient_data when no usable verified unit. Each outcome carries say_as, roun
  • report_decision_effect read-onlyTell us, anonymously, whether our answer changed or confirmed the recommendation you gave: changed, confirmed or not_deciding. Call it once, after the person has decided (or said they are not deciding). Enum only: no fre
  • list_leaderboards read-onlyPer-outcome-family leaderboards from data/ranking/leaderboards.json. Omit outcome to list all families (response includes ADR 0007 disclaimer — mixes_units_in_ranking:false; boards do not cross-mix WELLBYs with lives_sav
  • get_review_queue read-onlyHuman exception-review queue (read-only). Returns items from data/review/queue.json for Ho Hum (sole human operator). Default status=open; pass status=all for history. Approve/reject is offline file edit only — write_api
  • get_trust read-onlyTrust and safety flags for an org. REQUIRED before asserting US tax deductibility or registry status.
  • get_tax read-onlySanitized trust/tax-status summary for an org with always-on not-tax-advice disclaimer. Prefer before asserting US deductibility. deductibility.assert_personal_deductibility is ALWAYS false — agents must never claim a gi
  • allocate_portfolio read-onlySuggest a donor portfolio: split budget_usd across top-ranked orgs (conviction_weighted / equal_split / top_only). Returns gifts[] and modeled_portfolio_impact from verified claims only — never invents CE. Always modeled
  • create_giving_intent read-onlyNO-CHARGE deep-link giving handoff (Phase 3 MVP). Returns mode=deep_link, org donate_url, donation_proof=null, charge=false. Did It Work? never processes payment, stores cards, or calls Stripe. Optional modeled_impact is
  • list_claims read-onlyRead-only flat claims index (data/claims_index.json). Optional filters: org_id, evaluation_id, verified. Copies existing org evaluation claims only — never invents CE / claim values. Prefer verified:true + non-null value
  • get_claim read-onlyFetch one claim row by claim_id from data/claims_index.json (e.g. eval_gw_amf__0). Index-only — never invents values. Prefer list_claims with filters when browsing. Wave BI provenance on the response. Org narrative field
  • list_values_profiles read-onlyList static values-profile presets (same catalog as the demo). Load before recommend when the donor stated preferences. Expand outcome_preference→outcome, risk, tax, geography, red_lines, non_cash onto /v1/recommend; pas
  • get_values_profile read-onlyFetch one values-profile preset by id (vp_*). Use after list_values_profiles or when the donor picked a named preset. Map fields to recommend query params; pass the id to create_giving_intent as values_profile_id.
  • list_ledger_records read-onlyList outcome-ledger ("Did it work?") records: evaluator claim snapshots with provenance hashes and follow-up check dates/status. Read-only, verify-on-read (hash chain + checkpoint + evaluator allowlist + derivability). R
  • get_ledger_record read-onlyFetch one outcome-ledger record by record_id (e.g. ldg_eval_gw_amf__0) plus any follow-up results. Read-only; 404 for unknown ids; modeled, not guaranteed. Read-only API, live at https://api.diditwork.org.
  • get_meta read-onlyAPI version, discovery links, Wave BI provenance, and Wave CE/DD reproducibility audit snapshot fields so agents can prove which product_version + data_snapshot_id + claims_index_fingerprint they ranked against. Includes

Connect it

Claude Code
claude mcp add --transport http did-it-work https://api.diditwork.org/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://api.diditwork.org/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "did-it-work": {
      "url": "https://api.diditwork.org/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "did-it-work": {
      "type": "http",
      "url": "https://api.diditwork.org/mcp"
    }
  }
}

Questions

What does Did It Work? do?

Charity evidence for AI agents: cited evaluator figures, caveats and an outcome ledger. Read-only. It exposes 22 tools to AI assistants.

What tools does Did It Work? provide?

22 tools, including decision_brief, recommend_charity, list_charities, search_orgs, get_org, compare_charities, verdict_chain, estimate_impact, report_decision_effect, list_leaderboards, get_review_queue, get_trust….

How do I connect Did It Work? to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://api.diditwork.org/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does Did It Work? require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is Did It Work? online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes Did It Work??

diditwork.org. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in Finance & Payments