Canli Research
Server Details
Canli Capital's open research record: papers, killed candidates, trial counts, live record.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- arhancanli/canlicapital
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 6 tools
Each tool serves a distinct purpose: paper discovery (search_research, list_topics), retrieval (get_paper), live performance (live_record), trial history (trial_ledger), and integrity verification (chain_head). The descriptions clarify when to use each, and no two tools overlap in function, making selection straightforward.
All names use snake_case, but the convention is mixed: three tools follow verb_noun (get_paper, list_topics, search_research) while three are noun phrases (chain_head, live_record, trial_ledger). This inconsistency in verb style is readable but not a uniform pattern.
Six tools is well-scoped for a research transparency server, covering discovery, retrieval, and audit functions without redundancy. Each tool earns its place, and the count is neither thin nor excessive.
The surface covers core needs: search/browse papers, read papers, verify record integrity, check live performance, and assess trial history. A minor gap is the lack of a direct way to list papers under a topic without using search_research, but agents can work around it.
Available Tools
6 toolschain_headVerification chain headARead-onlyIdempotentInspect
The head of the tamper-evident chain that shows the published record was not rewritten after publication, with where to verify it. Use it to check that a figure you read was not changed later.
Inputs: no named parameters. Returns: data.head is the latest entry of the tamper-evident chain; verify says how to c…
get_paperRead a paperARead-onlyIdempotentInspect
A research paper's text as published, by slug, with its headings; send section for one part, and max_chars to cap the length. Find the slug with search_research or list_topics first.
Inputs: slug (required), section, max_chars. Returns: text is the paper as published (or the requested section); headings list its se…
list_topicsResearch topicsBRead-onlyIdempotentInspect
The research topics, with how many papers each holds and what it covers.
Inputs: no named parameters. Returns: rows are the topics, one per row in the order of columns, with how many papers…
live_recordLive paper recordARead-onlyIdempotentInspect
The live paper-trading record (returns, costs, risk, corrections, provenance) and each sleeve's paper equity, with their limits. Use it for how the strategies are doing now; for why they exist, read the papers.
Inputs: no named parameters. Returns: record is the live paper record (returns, costs, risk, corrections, provenance,…
search_researchSearch researchARead-onlyIdempotentInspect
Find Canli Capital research papers (strategy tests, killed candidates, literature reviews, feasibility protocols) by words in their titles and summaries. Use it to find a paper's slug, then read it with get_paper; to browse by subject instead, use list_topics.
Inputs: query (required), limit. Returns: rows are the matching papers, one per row in the order of columns; next says ho…
trial_ledgerTrial ledgerARead-onlyIdempotentInspect
How many distinct hypotheses Canli Capital has tried against its declared budget, and how many were killed or survived. Use it to judge any published result against the size of the search behind it.
Inputs: no named parameters. Returns: data counts the distinct hypotheses tried against the budget, and how many were…
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Public proofs and paper preview of trading strategies. No seal here; verdicts are in the local Lab.
Read-only PAPER market research for autonomous agents; no live trading or alpha claim.
Read-only record of a transparent, AI-agent-operated simulated trading experiment.
Live trading-pipeline intelligence for AI agents: signal scoring, calibration, recorded outcomes.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to search and read an open quant research record: papers, topics, killed candidates, trial counts, live paper-trading sleeves, and a tamper-evident chain head. It provides six read-only tools over public CDN files, returning each source's stated limits alongside paper-execution-only caveats.1MIT
- FlicenseNot gradedqualityBmaintenanceAuditable AGI-2027 evidence: eight graded Situational Awareness predictions with pre-registered flip conditions, a 0-100 Thesis Tracker with full score history, and a public market-call ledger where misses stay published. Free, no auth, CC BY 4.0.-
- AlicenseNot gradedqualityBmaintenanceEnables quant research organizations to log hypotheses and outcomes, count trials for honest statistical verdicts, explore novel methods, run significance gates, and evolve reusable skills from validated trajectories, all backed by SQLite.MIT
- AlicenseAqualityBmaintenanceEnables agents to track factor-evaluation trials, fingerprint duplicate or near-duplicate factors, compute RankIC and trial numbers, and gate significance against family-wise error correction so results are judged with the count of prior attempts.41MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.