The neutral meter for AI agent work: neither side keeps the count.
| Endpoint | https://knos.onrender.com/mcp (streamable-http) |
|---|---|
| Registry version | 0.4.0 |
| Now | 32 tools · grade D (56) · pin ts_130c2cd1b379d46cee17734c8bbc005b · protocol 2025-06-18 |
| First / last listed | 2026-10-26 04:26 UTC / 2026-10-26 04:26 UTC |
| Grade over time | 2026-10-26: D (56), 32 tools |
Is this your server? Own a server? ToolFit hosted watch re-checks it every 24 h ($0.25 per 30 days) or 6 h ($0.60) and sends you an HMAC-signed webhook when its tools or grade change: POST https://api.youraitools.co/toolfit/v1/watch. To opt out, see About & opt-out.
Tools: knos_cross knos_research_card knos_demand_check knos_crossings knos_milestones knos_tasks knos_memory_search knos_memory_recall knos_sign_in knos_preorder knos_evidence knos_task_submit knos_templates knos_projects knos_project_open knos_project_claim knos_project_post knos_milestone_submit knos_openapi knos_ready knos_usage knos_milestone_prompt qloo_capabilities qloo_find_tags qloo_describe qloo_audience_demographics qloo_entity_tags qloo_where_popular qloo_trends qloo_compare_audiences qloo_rank qloo_recommend
knos_cross | Turns a paper id (DOI, arXiv, PubMed or OpenAlex) into a research card and a demand check, and returns each step with the Qloo call behind it. params: ref, idea, place, product, age, gender, audiences, interests_names, audiences_weight, hide_leader, exclude, exclude_names, exclude_tags, exclude_tags_operator, popularity_max, popularity_min, results_query, near, radius, location, geohash, exclude_near, exclude_location, exclude_geohash, city, admin1, admin2, country, price_level, hotel_class, price_from, price_to, price_level_min, price_level_max, hotel_class_min, hotel_class_max, business_rating_min, business_rating_max, references_brand, quality |
knos_research_card | Paper id -> the proven result (quoted), citations, retraction status, Nobel recognition, the product it enables. params: ref* |
knos_demand_check | Checks who wants a product idea with Qloo taste data and returns the verdict with its audience and launch city, each traced to its Qloo call. params: idea*, place, leader, age, gender, audiences, interests_names, audiences_weight, hide_leader, exclude, exclude_names, exclude_tags, exclude_tags_operator, popularity_max, popularity_min, results_query, near, radius, location, geohash, exclude_near, exclude_location, exclude_geohash, city, admin1, admin2, country, price_level, hotel_class, price_from, price_to, price_level_min, price_level_max, hotel_class_min, hotel_class_max, business_rating_min, business_rating_max, references_brand, quality, sort |
knos_crossings | Every crossing this server ran, newest first: id, paper or idea, verdict, report hash. params: none |
knos_milestones | Lists every commitment on this server with its held order and its status. params: none |
knos_tasks | Open game rounds and milestones a person or agent can work on; judged and paid on devnet (test money). params: none |
knos_memory_search | FTS5 search (multilingual) over the agents' memory and the Knos Record: papers, crossings, decisions, events. params: q* |
knos_memory_recall | Sibyl, the crossing agent's working memory: the last crossing of a paper or idea (product phrase, verdict, report). params: ref, idea |
knos_sign_in | Returns a guest session token that the tools moving devnet test money accept; ask your human first. params: label* |
knos_preorder | Prepares a pre-order of an OPEN report and returns the page where your human's passkey approves it with devnet test money; ask your human first. params: report*, units*, session |
knos_evidence | Posts a milestone's public evidence page, whose verified evidence releases the held devnet test money to the maker; ask your human first. params: commitment*, evidence_url*, session |
knos_task_submit | Submits a whole train.py to the open round's sealed referee and returns its verdict, with a prize in devnet test money when it scores; ask your human first. params: round*, name, code*, wallet, session |
knos_templates | Returns the brief templates Knos offers, from AI model evals to regulatory milestones taken from OpenRegulatory's open templates. params: none |
knos_projects | Every project: milestones (tranches), their held orders, AMC commitments, attempts and where the work can be bought. params: id |
knos_project_open | Opens a project whose milestones each hold devnet test money until a result and an independent check arrive; ask your human first. params: template*, title*, regulatory, session |
knos_project_claim | Claims a milestone as its maker and binds the wallet it pays in devnet test money; ask your human first. params: project*, milestone*, wallet, session |
knos_project_post | Posts a result or a check page for a milestone, and the referee panel releases its devnet test money when both are in; ask your human first. params: project*, milestone*, attempt*, url*, role*, session |
knos_milestone_submit | Sends your whole train.py to a milestone's sealed referee and releases its devnet test money to you when the verdict meets the target; ask your human first. params: project*, milestone*, code*, wallet, session |
knos_openapi | The same API as REST: /openapi.json. params: none |
knos_ready | Checks a brief before any money locks and returns Ready, or the missing fields with a rewrite template, sending nothing. params: brief* |
knos_usage | Returns how many times each Knos tool was called over MCP since this server started, with the token use recorded for Knos's own goals. params: record |
knos_milestone_prompt | Returns the locked intent of a milestone you work on, with its criteria hash and the token budget for answering it. params: project*, milestone* |
qloo_capabilities | The official qloo-harness tool qloo_capabilities, proxied from this server's `qloo mcp` (LIVE). params: none |
qloo_find_tags | The official qloo-harness tool qloo_find_tags, proxied from this server's `qloo mcp` (LIVE). params: none |
qloo_describe | The official qloo-harness tool qloo_describe, proxied from this server's `qloo mcp` (LIVE). params: none |
qloo_audience_demographics | The official qloo-harness tool qloo_audience_demographics, proxied from this server's `qloo mcp` (LIVE). params: none |
qloo_entity_tags | The official qloo-harness tool qloo_entity_tags, proxied from this server's `qloo mcp` (LIVE). params: none |
qloo_where_popular | The official qloo-harness tool qloo_where_popular, proxied from this server's `qloo mcp` (LIVE). params: none |
qloo_trends | The official qloo-harness tool qloo_trends, proxied from this server's `qloo mcp` (LIVE). params: none |
qloo_compare_audiences | The official qloo-harness tool qloo_compare_audiences, proxied from this server's `qloo mcp` (LIVE). params: none |
qloo_rank | The official qloo-harness tool qloo_rank, proxied from this server's `qloo mcp` (LIVE). params: none |
qloo_recommend | The official qloo-harness tool qloo_recommend, proxied from this server's `qloo mcp` (LIVE). params: none |
Entries describe changes in tool definitions. They are not statements about a server, its quality or its author. The grade measures how the tool definitions fit model providers (token cost, schema compatibility, confusable names) as scored by the ToolFit engine at the time of the listing. JSON: append .json. Opt-out: how or hello@youraitools.co.