Canli Backtest
NPM · CANLI-BACKTEST-MCP
Lookahead-free backtests: point-in-time SEC factors, your prices, real costs, every variant counted.
Available components
Last scanned (57 minutes ago)
Scores higher than 53% of npm servers
Category Finance and Payments
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security99
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 3 of 17 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to arhancanli/canlicapital). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 4 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability54
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 604 tokens (~201/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage96
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 88% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
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.
- 14 Oct 26 +27
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- First check of Schema quality: fail functional
- First check of Tool coverage: 88 functional
- First check of Destructive annotations: pass functional
- First check of Schema quality: fail functional
- First check of Schema quality: good functional
- 13 Oct 26 50
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 18 Oct 2026 · Analysed npm/canli-backtest-mcp@0.1.2
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | arhancanli/canlicapital |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/arhancanli/canlicapital/.github/workflows/mcp-backtest-publish.yml@refs/tags/backtest-mcp-v0.1.2 |
| Rekor log index | 3244867003 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:f09ea89b65fb21676ded9d12defc737c377325a4f2f183d1e1c5c1c8dfa90622b8e04b989a82eb577849c54f3e6fe03def25ed639189eed7bfa771fac |
Background: How many MCP packages publish verified provenance →
Dependencies 17 packages
| Packages resolved | 17 |
|---|---|
| Stale | 3 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
backtest_signal Backtest a signal without lookahead ~316
Backtest a signal against your prices: rank, long and short quantiles, rebalance, trading only on what was known lag_days earlier, costs on actual trades. Pass ledger to judge the best of a search against all of it. A backtest measures one path of history under these costs; it does not establish that the signal will keep working.
| Name | Type | Req | Description |
|---|---|---|---|
| cost_bps | number | – | Cost per unit traded, in basis points. Default 10. |
| label | string | – | The variant's name in the ledger. Default: the settings. |
| lag_days | integer | – | Trading days between a signal becoming known and trading on it. Default 1, the minimum. |
| ledger | string | – | Record this run in a search ledger (created if new) and judge it against every run recorded there. |
| min_names | integer | – | Skip a rebalance with fewer ranked names. Default 5. |
| periods_per_year | number | – | Default 252 (daily prices). |
| prices_file | string | yes | CSV: a date column (YYYY-MM-DD) and one column of closing prices per ticker. |
| quantile | number | – | Fraction of ranked names in each leg. Default 0.2. |
| rebalance | – | – | Default monthly; or every N trading days. |
| side | string | – | Default long_short: long the top quantile, short the bottom. |
| signal_file | string | yes | CSV in the same shape; each row dated when its values became known (pit_factor writes this). |
No output schema declared.
No examples provided.
list_factors Point-in-time factors ~26
The point-in-time factors pit_factor builds from SEC filings, and what each measures.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
pit_factor Build a point-in-time factor ~187
Build a factor from SEC filings for a list of tickers, monthly from start to end, using only what had been filed by each date (restatements invisible until filed). Writes a signal CSV for backtest_signal. Values are what companies reported to the SEC in XBRL, as filed by each date; a company that files late, files outside XBRL or changes its tags can be missing.
| Name | Type | Req | Description |
|---|---|---|---|
| end | string | yes | – |
| factor | string | yes | One of roa, gross_margin, operating_margin, revenue_growth, asset_growth, accruals, or level:<measure> (revenue, net_income, assets, ...). |
| out_file | string | – | Where to write the signal CSV; default a new temporary file. |
| start | string | yes | – |
| tickers | array | yes | Tickers (or CIKs) to compute it for. |
No output schema declared.
No examples provided.
How do I install the Canli Backtest MCP server?
Canli Backtest runs locally as an npm package, launched with npx -y canli-backtest-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · canli-backtest-mcp
claude mcp add arhancanli-canli-backtest-mcp -- npx -y canli-backtest-mcp
What is the Canli Backtest MCP server?
Canli Backtest is an MCP server listed in the public MCP registry as io.github.arhancanli/canli-backtest-mcp. Lookahead-free backtests: point-in-time SEC factors, your prices, real costs, every variant counted. This page covers its npm package (canli-backtest-mcp).
Is the Canli Backtest MCP server safe to use?
Canli Backtest scores 77 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 18 October 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Canli Backtest MCP server expose?
Canli Backtest exposes 3 tools: list_factors, pit_factor, backtest_signal. Their descriptions and schemas cost roughly 529 tokens of context every time the server is loaded.
Is the Canli Backtest MCP server still maintained?
Canli Backtest is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Canli Backtest MCP server under?
Canli Backtest declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.