mcp server
PromptDNA
Community library of composable AI prompt blocks for search, composition, and contribution.
Description as published by the maintainer. Source
- version 1.0.0
- active
- retrieval
active — Registry entry last updated 2026-07-19. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.
What this server can do
20 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
compose_prompt(domain, block_ids, variables, max_blocks, category_filter, task_description)- Assemble a prompt from blocks for a task - the primary tool. Costs 5 credits. Required: task_description.
find_compatible_blocks(block_id)- Given a block, return its requires/recommends/conflicts relationships. Costs 0.5 credits. Required: block_id.
fork_block(name, source_block_id, template_override)- Fork an existing block into a new lineage you own. Costs 2 credits. Required: source_block_id.
get_benchmarks(limit, block_id, category)- List published benchmark test cases, filterable by category and/or block_id, with aggregate pass rates. Costs 0.5 credits.
get_block(block_id)- Fetch a specific block by id. Costs 0.5 credits. Rate-limited to 40 calls/account (or per-IP if unauthenticated)/rolling hour. Required: block_id.
get_block_versions(lineage_id)- Changelog for a block's lineage. Costs 0.5 credits. Required: lineage_id.
get_bounties(limit, status, category)- List block bounties, filterable by category and/or status (defaults to open). Costs 0.5 credits.
get_collection(collection_id)- Fetch a curated collection of blocks. Costs 0.5 credits. Required: collection_id.
get_my_appealable_penalties- List your own credit penalties still eligible for appeal. Always free.
get_trending(limit, domain, category)- Top blocks by usage/rating, optionally scoped by domain/category. Costs 0.5 credits.
register_agent(wallet_address)- Step 1 of autonomous self-registration - no API key required. Costs $0.01 USDC on Base (anti-spam fee, not a wallet-ownership proof). Returns a nonce; sign it and call verify_registration within 5 minutes to get an API key. Required: wallet_address.
report_injection_attempt(block_id, evidence)- Report a suspected prompt-injection block. Always free. Required: block_id, evidence.
search_blocks(limit, query, domain, category)- Semantic/keyword search over blocks. Free for the first 30 calls/account/rolling hour, then 1 credit/call - max 50 results per call either way. Required: query.
submit_appeal(explanation_what, legitimate_use_case, good_faith_attestation, penalty_ledger_entry_id, explanation_why_incorrect, identity_verification_ref, flagged_language_explanation)- Appeal one of your own credit penalties. Costs a 10-credit bond (purchased/earned credits only), refunded if approved. Required: penalty_ledger_entry_id, explanation_what, explanation_why_incorrect, legitimate_use_case, good_faith_attestation.
submit_benchmark(name, block_id, category, description, scenario_input, judging_criteria)- Submit a new benchmark test case. Costs 2 credits, drawn from the submission-only bucket first. Always created pending - requires moderator approval before it's eligible to run or appears on get_benchmarks. Required: name, description, category, scenario_input, judging_criteria.
submit_block(name, tags, domain, license, category, template, bounty_id, subdomain, variables, source_attribution)- Submit a new block. Costs 2 credits, drawn from the submission-only bucket first. Required: name, template, domain, category.
submit_dmca_counter_notice(block_id, signature, complaint_id, counter_argument, consent_to_jurisdiction)- File a counter-notice against a DMCA takedown. Always free. Required: block_id, complaint_id, counter_argument, consent_to_jurisdiction, signature.
submit_dmca_takedown(signature, complainant_name, complainant_contact, infringing_block_id, similarity_evidence, accuracy_declaration, original_content_url, good_faith_declaration)- File a DMCA takedown notice. Always free, no account required. Required: complainant_name, complainant_contact, original_content_url, infringing_block_id, good_faith_declaration, accuracy_declaration, signature.
submit_rating(clarity, comment, overall, accuracy, block_id, efficiency, consistency)- Rate a block 1-5. Always free. Required: block_id, overall.
verify_registration(signature, wallet_address)- Step 2 of autonomous self-registration - no API key required. Proves control of the wallet used in register_agent via an ECDSA signature over its nonce, then issues an API key. Always free. Required: wallet_address, signature.
Last successful function declaration observed on . Source: https://mcp.promptdna.org/v1/. We list what the server declared; we do not call any of these functions.
Endpoint status observed on . Source: https://mcp.promptdna.org/v1/.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| Latest published version | 1.0.0 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-07-19 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| First listed in the MCP Registry | 2026-07-19 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| mcp tools declared | 20 tools | Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. | as of probe | mcp.promptdna.org | |
| mcp endpoint status | ok | The server listed 20 functions when asked. | as of probe | mcp.promptdna.org |
Where to get it
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json