Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Tapebasis

PYPI · TAPEBASIS · 2 COMPONENTS

Market data from multiple independent providers, compared with clear provenance.

70 Trust /100

Last scanned (17 hours ago)

Scores higher than 63% of PyPI servers

Category Finance and Payments

Trust breakdown (7 categories)

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 Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
  • 2 of 49 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability69
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 11653 tokens (~200/item across 58 items; 56 tools + 2 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 Management20
  • Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 56 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 58 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
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

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.

  • 21 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

  • 20 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 19 Nov 26 0
    • Malware scan: unverified → pass ▲ security
    • Package version: 1.2.0 → 1.2.1 functional
  • 18 Nov 26 +1
    • Schema quality: 7269 → 11171 ▼ functional
    • Schema quality: 7269 → 8914 ▼ functional
    • Package version: 1.1.2 → 1.2.0 functional
    • Package version: 1.1.2 → 1.1.4 functional
  • 17 Nov 26 +1
    • Stability: unverified → 0.07 ▲ functional
    • Package version: 1.0.0 → 1.1.2 functional
    • Package version: 1.0.0 → 1.1.1 functional
  • 15 Nov 26 52

    First indexed and scored.

Diagnostics

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 21 Nov 2026 · Analysed pypi/tapebasis@1.2.1

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi
Reason No attestation published

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend Known build tool setuptools.build_meta

Background: Why install scripts are a supply-chain risk →

Dependencies 49 packages
Packages resolved 49
Stale 2
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 56 exposed · ~10,476 tokens

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 →

Tool Tokens
stock_screener_filters ~41

Finviz's full screener filter catalogue (Finviz-only). Returns: Envelope labelled ``FINVIZ`` with the machine-readable filter list.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

stock_short_positioning ~206

Read short, FTD and off-exchange history with an ordinary API key. An account that lacks a dataset receives an explicit provider error; no provider fallback or empty downgrade occurs. Args: symbol: US-listed stock or ETF ticker. limit: Rows per dataset, clamped to 1 through 500. start_date: Optional inclusive ISO date filter. end_date: Optional inclusive ISO date filter. include_fails_to_deliver: Fetch SEC fails-to-deliver balances when true. include_off_exchange: Fetch weekly FINRA ATS and OTC volume when true. Returns: Envelope with unchanged short-interest, short-volume and selected FTD and off-exchange datasets, each retaining its distinct reporting delay.

NameTypeReqDescription
end_date–––
include_fails_to_deliverboolean––
include_off_exchangeboolean––
limitinteger––
start_date–––
symbolstringyes–

Structured output declared, but exposes no named fields.

No examples provided.

stock_why_moving ~147

Finviz's own explainer plus the latest 10 stories for a ticker. The editorial headline, summary, sentiment and catalyst remain Finviz-only. ``data.news`` separately merges TradingView/Marketaux, Finviz and Yahoo, naming each story's providers and consensus rather than replacing the editorial feed with generic headlines. Args: symbol: Ticker. Returns: Envelope labelled ``FINVIZ`` for the editorial leg, with ``data.news`` alongside it. If the editorial feed fails, ``data`` stays null and the independent news is in top-level ``news`` beside the preserved error.

NameTypeReqDescription
symbolstringyes–

Structured output declared, but exposes no named fields.

No examples provided.

tapebasis_health ~370

Probe every upstream and report whether any provider's API drifted. Every other tool reads the cached verdict from this monitor and adds a warning when a provider's upstream schema has changed or is down. Call this with ``refresh=True`` to force an immediate re-probe (otherwise the cached result is reused for ``TAPEBASIS_HEALTH_TTL`` seconds). Drift is judged on the fields this server actually reads. An upstream that drops a key nobody looks at is serving every number here correctly and is not reported as an outage, which is what made every response ``degraded: true`` when two cosmetic keys were removed upstream. ``accept_baseline=True`` re-records the current payload shape as the new baseline. Use it after an upstream change you have checked and adapted to: without it, a cosmetic rename keeps reporting ``DRIFT`` forever, and the only way out was deleting the state file. The report also carries ``rate_limits``: per-provider pacing, cooldown and cache state. A provider can be ``OK`` and still be cooling down after a ``429``, which is what an agent needs to know before it retries. Args: refresh: Force fresh probes instead of using the cached verdict. accept_baseline: Re-record the current shape as the baseline and clear drift. Probes that are ``DOWN`` keep their old baseline. Returns: Envelope whose ``data`` carries ``providers`` (``OK``/``DRIFT``/ ``DOWN``/``UNKNOWN`` per provider), ``degraded``, ``issues``, ``rate_limits`` and the per-probe baseline comparison.

NameTypeReqDescription
accept_baselineboolean––
refreshboolean––

Structured output declared, but exposes no named fields.

No examples provided.

tapebasis_tool_map ~118

List every tool, which providers back it, and how it is cross-checked. Useful for an agent that needs to know whether a given capability is multi-source (``ALL``, which can include ``SA`` or ``BLOOMBERG``), served by a single provider (``TRADINGVIEW``/``FINVIZ``/``YAHOO``/``SA``/ ``BLOOMBERG``) or analysis generated by one provider only. This tool performs no upstream requests.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

technical_analysis ~242

Multi-indicator technical analysis, price cross-checked across providers. TradingView computes the full indicator stack (RSI, MACD, EMAs, Bollinger, ATR, ADX, structure, trade setup). Finviz's snapshot and Yahoo's chart API independently provide price, RSI(14), ATR(14) and volume, which are compared here, so the numbers the analysis is built on are corroborated rather than taken on trust. The TradingView leg uses its resolved symbol and venue, never a bare ticker redirected by the caller's default exchange. Args: symbol: Ticker. exchange: TradingView exchange prefix (``NASDAQ``, ``NYSE``, ``BIST``, …). timeframe: ``5m``, ``15m``, ``1h``, ``4h``, ``1D``, ``1W``, ``1M``. Returns: Envelope whose ``data.analysis`` is the TradingView analysis and ``data.cross_check`` holds the per-provider comparison.

NameTypeReqDescription
exchangestring––
symbolstringyes–
timeframestring––

Structured output declared, but exposes no named fields.

No examples provided.

Install

How do I install the Tapebasis MCP server?

Tapebasis runs locally as a PyPI package, launched with uvx tapebasis. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · tapebasis

# add to Claude Code
claude mcp add giraygokirmak-tapebasis -- uvx tapebasis
Common questions

What is the Tapebasis MCP server?

Tapebasis is an MCP server listed in the public MCP registry as io.github.giraygokirmak/tapebasis. Market data from multiple independent providers, compared with clear provenance. This page covers its PyPI package (tapebasis).

Is the Tapebasis MCP server safe to use?

Tapebasis scores 70 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. 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 Tapebasis MCP server expose?

Tapebasis exposes 56 tools: stock_quote, stock_prices, stock_screener, market_indices, stock_news, and 51 more. Their descriptions and schemas cost roughly 10,476 tokens of context every time the server is loaded.

Is the Tapebasis MCP server still maintained?

Tapebasis is still listed as active in the MCP registry. We last reached this channel on 21 November 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 Tapebasis MCP server under?

Tapebasis declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the Tapebasis MCP server?

VerifyMCP ran 16 checks on Tapebasis, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.