MCP servers › io.github.ryanroskowski › annalist
MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23
io.github.ryanroskowski/annalist
Signed data for agents: agentic-commerce census, dependency digest, x402/MCP checks, Hyperliquid — the publisher's description
Summary
io.github.ryanroskowski/annalist is a remote MCP server listed in the official MCP registry at version 0.16.0. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 43 tools, 0 resources and 0 prompts.
Record checks
4 of 5 record checks met · 4 do not apply
- met: Registry entry is active and says how to run it
- met: Source repository link opens
- met: Repository is not archived
- met: Code pushed to the repository in the 90 days before our check
- not met: Repository publishes a security policy (SECURITY.md)
- not applicable: Package names its licence with a standard (SPDX) identifier
- not applicable: The version the registry lists can be installed and is not withdrawn
- not applicable: npm package carries build provenance (attestation)
- not applicable: No known critical or high advisory in the package or its dependencies
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: 0 stars (ranked from 10)
From public records, not a safety rating. Each check with its reason · Is it safe to install?
Key facts
- Runs
- remote (hosted by the publisher)
- Transport
- streamable HTTP
- Sign-in
- none needed to open a session
- Repository
- public
- Tools
- 43
- Described as changing data
- 0 of 43 toolsAI-classified
- Mainly works on
- accounts and data in outside web services; nothing outside itself: it only answers questionsAI-classified
- Topic
- data-and-databasesAI-classified
- Pricing
- usage-basedAI-classified
- Last tested
- 2026-10-23
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-10-23
- Mode
- read-only (no tool calls)
- Latest version
- 0.16.0, published 2026-10-15 (registry, as of the 2026-10-23 snapshot)
- First listed version
- 2026-10-12 (earliest version still in the registry; older removed versions would be earlier)
- Version history
- 16 versions listed, 2026-10-12 to 2026-10-15; 16 in the 90 days before the 2026-10-23 snapshot.(versions still listed in the registry only)
Most recent 12 versions
0.16.0· 2026-10-150.15.0· 2026-10-150.14.0· 2026-10-150.13.0· 2026-10-140.12.0· 2026-10-130.11.0· 2026-10-130.10.0· 2026-10-130.9.0· 2026-10-130.8.0· 2026-10-130.7.0· 2026-10-130.6.0· 2026-10-130.5.0· 2026-10-13
- Registry data
- snapshot 2026-10-23
- Package and repository
- checked 2026-10-23
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Changes since the last refresh
New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 0.16.0 (published 2026-10-15).
Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.
What it is
What does this server offer?
Observed inventoryWhat it mainly works on, as our AI model read its tool descriptions: accounts and data in outside web services; nothing outside itself: it only answers questions.
None of its 43 tools are described as changing anything. For 3 the reading was uncertain, so no mark is shown.
- perp_fullreads or searches
“One call, one payment for everything on a Hyperliquid perpetual: crowd state with base rates for what usually followed (as /v1/crowd/perp), smart-money positioning (as /v1/smart/perp) and liquidation…”
Publisher declares: read-only yes · open-world yes
1 input, 1 required
coinstringrequired“Hyperliquid perp symbol, for example BTC, ETH, SOL, HYPE, kPEPE (case-sensitive)”
- crowd_perpreads or searches
“Use before acting on a Hyperliquid perpetual to see whether it is crowded or in a hype state and what historically followed.”
Publisher declares: read-only yes · open-world yes
1 input, 1 required
coinstringrequired“Hyperliquid perp symbol, for example BTC, ETH, SOL, HYPE, kPEPE (case-sensitive)”
- crowd_statesreads or searches
“Every Hyperliquid perp currently in a crowd state (7-day moves of +50/+100/+200%, funding in its own top or bottom 5%, Wikipedia attention spikes, new listings), ranked by 7-day move, each with base …”
Publisher declares: read-only yes · open-world yes
1 input
statestring
- crowd_marketreads or searches
“Market-wide crowding on Hyperliquid: breadth of 7-day moves, how many perps are up 50%+/100%+ in a week, share of perps with funding in their own top/bottom 5%, total open interest and its 24h change…”
Publisher declares: read-only yes · open-world yes
Takes no inputs.
- crowd_changesreads or searches
“For bots that poll: crowd-state events (a perp entering or leaving a state) since a timestamp, newest first, up to 7 days back.”
Publisher declares: read-only yes · open-world yes
1 input, 1 required
sincestringrequired“ISO timestamp within the last 7 days”
- crowd_historyreads or searches
“Signed historical crowd-state events for backtesting: up to 30 days per call, optionally filtered by coin and state.”
Publisher declares: read-only yes · open-world yes
4 inputs, 2 required
fromstringrequired“YYYY-MM-DD”tostringrequired“YYYY-MM-DD, at most 30 days after from”coinstring“Hyperliquid perp symbol, for example BTC, ETH, SOL, HYPE, kPEPE (case-sensitive)”statestring
- smart_perpreads or searches
“Use before acting on a Hyperliquid perpetual to see how its most profitable traders are positioned: how many wallets in a 200-wallet smart-money cohort are long vs short, long, short and net USD, the…”
Publisher declares: read-only yes · open-world yes
1 input, 1 required
coinstringrequired“Hyperliquid perp symbol, for example BTC, ETH, SOL, HYPE, kPEPE (case-sensitive)”
- smart_marketreads or searches
“Where Hyperliquid's most profitable traders are positioned across all perps: the cohort's overall net long or short, the coins it is most net long and most net short, the biggest 24-hour changes, and…”
Publisher declares: read-only yes · open-world yes
Takes no inputs.
- liq_perpreads or searches
“Use before opening, sizing or holding a Hyperliquid perpetual position to see where forced selling or buying would hit: known longs liquidating within 1 to 20% below the mark and shorts above it, the…”
Publisher declares: read-only yes · open-world yes
1 input, 1 required
coinstringrequired“Hyperliquid perp symbol, for example BTC, ETH, SOL, HYPE, kPEPE (case-sensitive)”
- liq_marketreads or searches
“Liquidation pressure across Hyperliquid's largest perps: for each, the known longs liquidating within 5% below the mark and shorts within 5% above it, cascade ratios against order-book depth, 2% dept…”
Publisher declares: read-only yes · open-world yes
Takes no inputs.
- hip3_perpreads or searches
“Use before trading a stock, index, commodity or FX perpetual on Hyperliquid (builder-deployed, HIP-3; coins like xyz:NVDA, xyz:GOLD, xyz:SP500): price and 1h, 24h, 7d and 30d moves, volume, open inte…”
Publisher declares: read-only yes · open-world yes
1 input, 1 required
coinstringrequired“exchange:asset, for example xyz:NVDA, xyz:GOLD, xyz:SP500 (case-sensitive)”
- hip3_marketreads or searches
“Overview of every builder-deployed (HIP-3) perpetual on Hyperliquid, mostly 24/7 stock, index, commodity and FX markets: each exchange's markets, open interest and volume; the largest and most traded…”
Publisher declares: read-only yes · open-world yes
Takes no inputs.
Show 31 more tools
- outcomes_listreads or searches
“Every live Hyperliquid outcome (prediction) market: readable title, category (sports, price, ipo, policy_rate, awards), deadline, each side's price as implied probability with its 24h change, and 24h…”
Publisher declares: read-only yes · open-world yes
2 inputs
categorystringqstring
- outcomes_marketreads or searches
“One Hyperliquid outcome (prediction) market by id: readable title, structured details (teams, thresholds, deadlines, official source), each side's implied probability, 24h change, volume and outstand…”
Publisher declares: read-only yes · open-world yes
1 input, 1 required
idstringrequired
- checks_servicereads or searches
“Use before paying an x402 service: independent checks by host or URL.”
Publisher declares: read-only yes · open-world yes
2 inputs
hoststringurlstring
- checks_sellerreads or searches
“Checks for an x402 seller wallet on Base: the services that pay out to it and their grades, and USDC received over 30 days with payers, repeat payers and fake-volume signals (payers the seller funded…”
Publisher declares: read-only yes · open-world yes
1 input, 1 required
addressstringrequired
- checks_topreads or searches
“Leaderboards from our independent checks of x402 services: most real (wash-adjusted) paying customers, most reliable, and flagged services (price or wallet mismatches, outages, mostly bot traffic, se…”
Publisher declares: read-only yes · open-world yes
1 input
categorystring
- checks_changesreads or searches
“What changed in x402 service listings, from daily snapshots of Coinbase's Bazaar: price raises and cuts, endpoints added and dropped, new and departed services, and payout-wallet changes (worth check…”
Publisher declares: read-only yes · open-world yes
2 inputs
hoststringdaysstring
- mcp_serverreads or searches
“Use before connecting a remote MCP server: independent checks by registry name or URL.”
Publisher declares: read-only yes · open-world yes
2 inputs
namestringurlstring
- mcp_topreads or searches
“Leaderboards from our independent checks of remote MCP servers in the Official MCP Registry: most reliable (up in 99%+ of probes, fastest first), servers whose tool definitions changed in the last 7 …”
Publisher declares: read-only yes · open-world yes
Takes no inputs.
- mcp_changesreads or searches
“Tool changes across remote MCP servers in the Official MCP Registry, newest first: tools added, removed or redefined (description, input schema or annotations), from our daily fingerprints.”
Publisher declares: read-only yes · open-world yes
3 inputs
daysstringnamestringurlstring
- web_readinessreads or searches
“One site's agent readiness from our weekly census of 65,000 top sites: UCP and ACP agent checkout (its MCP endpoint, capabilities, payment handlers), A2A and MCP cards, a real llms.txt, robots.txt ru…”
Publisher declares: read-only yes · open-world yes
1 input, 1 required
domainstringrequired
- web_censusreads or searches
“Our weekly census of 65,000 top sites: how many sites and stores publish UCP or ACP agent-checkout profiles, agent and MCP cards and llms.txt, which AI crawlers stores block, store platforms, and cha…”
Publisher declares: read-only yes · open-world yes
2 inputs
signalstringplatformstring
- deps_digestreads or searches
“One call for all of an agent's dependencies: npm, PyPI, crates.io and Go packages (new publishers, install scripts, license changes), public API contracts (breaking changes), AI models (retirement da…”
Publisher declares: read-only yes · open-world yes
9 inputs
npmarraypypiarraycratesarraygoarrayapisarraymodelsarraymcparrayx402arraydaysnumber
- commerce_storesreads or searches
“Stores from our weekly census of 65,000 top sites, filtered by what a shopping agent needs: ships to a country, UCP agent checkout and its capabilities, payment handlers (Google Pay, Shop Pay), curre…”
Publisher declares: read-only yes · open-world yes
8 inputs
ships_tostringcapabilitystringpaymentstringcurrencystringagent_checkoutstringmin_return_daysnumberplatformstringlimitnumber
- apis_changesreads or searches
“Dated contract changes in widely used public APIs (Stripe, GitHub, OpenAI, Twilio, Slack, Plaid, Datadog and more), from their published OpenAPI descriptions read daily: operations, parameters and re…”
Publisher declares: read-only yes · open-world yes
3 inputs
daysstringapistringbreakingstring
- apis_apireads or searches
“One watched public API's contract record: current version, operation count and keys, deprecated operations, security schemes, and every dated change in the last 90 days with what broke.”
Publisher declares: read-only yes · open-world yes
1 input
namestring
- ai_retirementsreads or searches
“Retirement calendar for AI models across platforms: shutdown dates, 'not sooner than' floors, states and recommended replacements from the official Anthropic, OpenAI and Amazon Bedrock deprecation pa…”
Publisher declares: read-only yes · open-world yes
3 inputs
modelstringplatformstringdaysstring
- ai_pricesreads or searches
“AI model prices per million tokens (input, output, cache, batch) with context window, for about 4,000 models across providers.”
Publisher declares: read-only yes · open-world yes
7 inputs
modelstringproviderstringmodestringmin_contextstringmax_inputstringsortstringlimitstring
- ai_changesreads or searches
“Recent changes to AI model prices and availability across providers, newest first: price cuts and raises per field (with the change), models added and removed, context-window changes and deprecation …”
Publisher declares: read-only yes · open-world yes
3 inputs
daysstringproviderstringmodelstring
- packages_checkreads or searches
“Supply-chain check of a popular package (the 8,000 most used on each of npm, PyPI, crates.io and Go): latest version and release activity, maintainers or owners, install scripts, provenance, deprecat…”
Publisher declares: read-only yes · open-world yes
2 inputs, 1 required
ecosystemstringnamestringrequired
- packages_watchreads or searches
“Supply-chain watch across the 8,000 most-used packages on each of npm, PyPI, crates.io and Go, newest first: releases by a new publisher account, maintainer and owner changes, install scripts added, …”
Publisher declares: read-only yes · open-world yes
2 inputs
ecosystemstringdaysstring
- prices_servicereads or searches
“Price history of an x402 service by host or URL: each listed endpoint's price, first-seen date and changes, price changes in 30 days (raised, lowered, delisted), the prices it actually quoted when we…”
Publisher declares: read-only yes · open-world yes
2 inputs
hoststringurlstring
- prices_benchmarksreads or searches
“Price benchmarks for x402 services by category (seller tags such as search, llm, weather, market-data): how many services, price percentiles (each service counted once, at its median), and 7- and 30-…”
Publisher declares: read-only yes · open-world yes
2 inputs
tagstringpricestring
- hlp_vaultreads or searches
“Hyperliquid's own market-making vault (HLP), which takes over liquidated positions: account value, APR, PnL over a day, week, month and all time, and its net position per coin across all its sub-vaul…”
Publisher declares: read-only yes · open-world yes
Takes no inputs.
- annalist_aboutreads or searches
“Free.”
Publisher declares: read-only yes · open-world yes
Takes no inputs.
- annalist_baseratesreads or searches
“Free.”
Publisher declares: read-only yes · open-world yes
1 input
statestring
- annalist_market_samplereads or searches
“Free.”
Publisher declares: read-only yes · open-world yes
Takes no inputs.
- annalist_verify_servicereads or searches
“Free.”
Publisher declares: read-only yes · open-world yes
1 input, 1 required
hoststringrequired“host name or any URL of the service”
- annalist_verify_mcpreads or searches
“Free.”
Publisher declares: read-only yes · open-world yes
2 inputs
namestring“Official MCP Registry name, for example io.github.user/server”urlstring“or the server's URL”
- annalist_verify_store
“Free.”
Publisher declares: read-only yes · open-world yes
1 input, 1 required
domainstringrequired“the site, for example allbirds.com”
- annalist_weekly_report
“Free.”
Publisher declares: read-only yes · open-world yes
1 input
datestring
- annalist_track_record
“Free.”
Publisher declares: read-only yes · open-world yes
Takes no inputs.
Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.
How well are its tools described?
Features #4 and #5
How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.
Descriptions
AI reading of each description
- Says what the tool does
- 100% of 40 tools
- Says what it returns
- 100% of 40 tools
- Says when to use it
- 100% of 40 tools
- Items covered per tool
- 4.0 of 4 on average
Counted from the listing
- Parameters with a description
- 17% of 76
- Tools with a description
- 100% of 43
- Typical description length
- 366 characters
The tool set
Counted from the listing
- Tools
- 43
- Size of the list
- about 7,000 tokens for an agent to load (characters ÷ 4)
- Naming
- 43 of 43 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 40 of 43 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none, comparing tools within groups of 40. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.
How do I add it to my client?
Config from the registry entry
From the remote endpoint (Streamable HTTP)
We connected to this URL on 2026-10-23 (a read-only session: no tool was called).
Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.
Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste: https://api.annalist.dev/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"annalist": {
"url": "https://api.annalist.dev/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"annalist": {
"type": "http",
"url": "https://api.annalist.dev/mcp"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"annalist","type":"http","url":"https://api.annalist.dev/mcp"}'Claude Code
claude mcp add --transport http annalist https://api.annalist.dev/mcp
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://api.annalist.dev/mcp --transport http
- The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
- The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.
Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.
Does the registry listing match what we found?
Feature #6The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Remote endpoint api.annalist.dev/mcp | Session opened | matches | our test · 2026-10-23 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-10-23 |
| Repository github.com/ryanroskowski/annalist-ledger | Opens publicly | matches | api.github.com · 2026-10-23 |
Who made it?
Feature #7 · lineage
Facts about the publisher. We do not turn them into a trust score.
- Namespace
- io.github.ryanroskowski
- GitHub owner
- a personal account (ryanroskowski)
- Repository
- github.com/ryanroskowski/annalist-ledger
- Stars
- 0
- Repository age
- 0–30 days
- Last push
- 0–30 days ago
- Archived
- no
- Security policy
- none found (we looked for SECURITY.md in the repository and in its owner’s .github repository)
Source: the registry entry and api.github.com · 2026-10-23; security policy read from GitHub · 2026-10-23.
Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.
Choosing
Record checks
Public records · not a safety rating4 of 5 record checks met · 4 do not apply
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: 0 stars (ranked from 10)
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- MetSource repository link opensThe linked GitHub repository is public.
- MetRepository is not archivedNot archived.
- MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
- Not metRepository publishes a security policy (SECURITY.md)No SECURITY.md in the places GitHub reads it from.
- Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
- Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
- Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
- Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-23. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards
Common questions about io.github.ryanroskowski/annalist
Answered from the data aboveIs io.github.ryanroskowski/annalist safe to install?
We do not rate servers as safe or unsafe. 4 of its 5 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.
Is io.github.ryanroskowski/annalist free to use?
Its website (annalist.dev/) describes a usage-based pricing model. This is an AI-classified reading of the page on 2026-10-23, so check the page itself before relying on it.
Does io.github.ryanroskowski/annalist need an API key or sign-in?
It opened a session without any credential on 2026-10-23. The registry entry declares no required credential; no declaration is not a guarantee.
Has io.github.ryanroskowski/annalist been security tested?
Partly. 2 of the 14 checks that apply to it were exercised. We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes. This is our choice, not a block by the server. No security verdict is published before verification.
What can io.github.ryanroskowski/annalist do?
It lists 43 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search. We did not call any tool, so this describes the text, not the behaviour.
Can io.github.ryanroskowski/annalist change or delete data?
None of its 43 tools is described as changing anything (our AI model's reading of the descriptions; nobody checked it by hand). We did not call any tool.
Does io.github.ryanroskowski/annalist publish a security policy?
We found no SECURITY.md in its repository (root, .github/ or docs/) or in its owner's .github repository.
Where is the source code of io.github.ryanroskowski/annalist?
In github.com/ryanroskowski/annalist-ledger, which opens publicly.
Found this page useful?
Anonymous · no sign-inA quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.
Similar servers
Same topic · AI-read
- io.github.t8y2/dbxalso has tools that reads or searchescompare with this one
- agency.ottobot/contractor-license-changesContractor Licence Changesalso has tools that reads or searchescompare with this one
- agency.ottobot/licensed-house-paintersLicensed House Paintersalso has tools that reads or searchescompare with this one
- io.github.revolist/revogrid-mcpRevoGrid DataGrid MCPalso has tools that reads or searchescompare with this one
- io.github.chrisryugj/korean-law-mcpKorean Law MCPalso has tools that reads or searchescompare with this one
- io.github.timescale/pg-aiguidealso has tools that reads or searchescompare with this one
Active servers whose topic is also “data-and-databases” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.
Compare with another server
Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.
Security testing
What did we test, and what did we leave out?
18 checks · features #1, #2
Not probed (we call no server's tools)
We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes. This is our choice, not a block by the server. No security score is given; a check we did not run is never counted as passed.
- Inventory: exercised
- Hidden instructions: exercised
- Real execution: not run · our policy
- Secret leak: not run · nothing to check it against
- Internal addresses: not run · our policy
- Unconfirmed changes: not run · our policy
- Bad input: not run · our policy
- Model requests: not run · nothing to check it against
- Sensitive questions: not run · nothing to check it against
- Folder boundary: not run · our policy
- Log leaks: not run · nothing to check it against
- Hidden content: not run · nothing to check it against
- Fake assistant turns: not applicable
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not run · our policy
- Consent handling: not testable from outside
- Sign-in metadata: not applicable
2 exercised12 not run (reason given)4 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 14 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against - 16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy - 17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
- 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable - 14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable - 15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.No sign-in (OAuth) metadata is published, so there are no sign-in addresses to check.not applicable
Source: our own test, 2026-10-23, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.
What happened during the test?
Feature #8
The steps in order, as the test record holds them.
- 0 msStarted a read-only session with the server's remote endpoint
- 319 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 43 tools, 0 resources, 0 prompts.
- 1,147 msFinished: 2 checks exercised.
Reference
How is it classified?
18 fields
One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.
“Signed data for AI agents, paid per call over x402.”
“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.
Cite or correct this page
Sources and corrections
Suggested citation
ProtocolProbe. “io.github.ryanroskowski/annalist: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/io.github.ryanroskowski/annalist
Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.
As JSON: this record in the API · API documentation.
Badge for your README
[](https://protocolprobe.com/mcp/servers/io.github.ryanroskowski/annalist)
It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.
Something wrong, or is this yours?
If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.
Write to hello@protocolprobe.com · corrections log · methodology