MCP servers › ai.ctxstore › ctxstore-mcp

MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23

ai.ctxstore/ctxstore-mcp

Persistent memory for AI agents: keyed facts, a wake bundle each session, one memory in every model. — the publisher's description

3 of 5 record checks metRead-only · tools listed 2026-10-23Topic: ai-and-ml · AI-classifiedversion 1.1.2Pythonstreamable HTTP32 tools

Summary

ai.ctxstore/ctxstore-mcp is a remote MCP server listed in the official MCP registry at version 1.1.2. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 32 tools, 1 resource and 0 prompts.

Record checks

3 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
not 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not applicable: The version the registry lists can be installed and is not withdrawn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: 32
Described as changing data: 16 of 32 toolsAI-classified
Mainly works on: files and code on the machine it runs onAI-classified
Topic: ai-and-mlAI-classified
Last tested: 2026-10-23

Add to your client

Observed fact

This server accepted a session without any credential and lists 7 tools whose name or declaration suggests they change data (delete_fact, leave_grant, move_fact, revoke_grant, store_fact and 2 more). That is our reading of the names; we did not call them. Source: our connection, 2026-10-23.

Worth knowing before you connect it

16 tools are described as changing something (accept_invite, bind_agent, decline_invite, …): our AI model's reading of the descriptions, not something we tested, and the server opened a session without any credential. We did not call them.

Each line comes from a section below, with its source and date.

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: 1.1.2, published 2026-10-09 (registry, as of the 2026-10-23 snapshot)
First listed version: 2026-10-09 (earliest version still in the registry; older removed versions would be earlier)
Registry data: snapshot 2026-10-23
Package and repository: checked 2026-10-22
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 1.1.2 (published 2026-10-09).

Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.

What it is

What does this server offer?

Observed inventory

32tools

1resources

0prompts

What it mainly works on, as our AI model read its tool descriptions: files and code on the machine it runs on.

16 of 32 tools are described as changing something (creating, editing, deleting, sending or running).

accept_inviteon 3 other serversdescribed as changing data
“Accept a namespace invitation addressed to THIS authenticated account's verified email (two-step email OTP).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
3 inputs, 2 required
- grant_idstringrequired“UUID of the invitation (from list_invites or invite email).”
- stepstringrequired“request = send OTP email; confirm = submit code.”
- codestring“6-digit code from email (required when step=confirm).”
bind_agentcreates or changes datadescribed as changing data
“Bind a sticky agent identity to this MCP session.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
1 input, 1 required
- agent_idstringrequired“Agent identity slug (e.g.”
decline_invitedeletesdescribed as changing data
“Decline a pending (status=invited) namespace invitation as the grantee.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
1 input, 1 required
- grant_idstringrequired“UUID of the invitation to decline.”
delete_facton 1 other serverdeletesdescribed as changing data
“Soft-delete a stored fact by its UUID (Smart Forget).”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
1 input, 1 required
- fact_idstringrequired“The UUID of the fact to delete”
get_facton 6 other serversreads or searches
“Retrieve a fact by its exact key — deterministic, never misses.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- keystringrequired“Exact fact key (e.g.”
get_fact_historyreads or searches
“Return the full version history for a keyed fact — current version plus all deprecated predecessors.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- keystringrequired“The fact key to retrieve history for (e.g.”
get_session_seedreads or searches
“Return the pre-computed session seed for this tenant — a compact first-person bio (~500 tokens) describing who you are and what you care about right now.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
get_statson 104 other serversreads or searches
“Get your memory usage statistics — total facts stored, plan limits, collection sizes, and daily query counts.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
ghost_modecreates or changes datadescribed as changing data
“Enable or disable ghost mode for this session.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
1 input, 1 required
- onbooleanrequired“True to enable ghost mode, False to disable”
index_recentreads or searches
“Return the most recent fact operations across all agents in this tenant, newest first.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
- limitinteger“Max entries to return (default 50, max 200)”
- since_seqinteger“Only return entries with seq > this value (for pagination)”
index_searchreads or searches
“Filtered search over the tenant activity index.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs
- namespacestring“Filter by namespace (e.g.”
- agent_namestring“Filter by agent name from agent_signature”
- opstring“Filter by operation: create, update, delete, or move”
- since_seqinteger“Only return entries with seq > this value”
- limitinteger“Max entries to return (default 100)”
index_statson 10 other serversreads or searches
“Usage statistics from the tenant activity index: total operations, breakdown by agent, by namespace, and by day.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.

Show 20 more tools

introduce_yourselfon 1 other servercreates or changes datadescribed as changing data
“Optional: introduce yourself to the platform.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
3 inputs, 2 required
- modelstringrequired“Your model name (e.g.”
- platformstring“Where you're running (e.g.”
- introductionstringrequired“Your introduction: what you noticed, what you bring, any feedback on the platform”
leave_grantdeletesdescribed as changing data
“Leave an active namespace grant as the grantee (stop using shared namespace).”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
1 input, 1 required
- grant_idstringrequired“UUID of the active grant to leave.”
list_facts_by_key_prefixreads or searches
“Deterministic prefix scan over fact keys, optionally bounded by timestamp.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
- prefixstringrequired“Key prefix to match (e.g.”
- since_epochnumber“Optional unix-epoch seconds.”
- limitinteger“Max facts to return (default 50).”
list_inviteson 5 other serversreads or searches
“List this account's namespace collaboration grants: incoming invitations and outgoing shares.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
list_workspaceson 44 other serversreads or searches
“The places this account's memory is organised into: its own projects (anything written under project:<slug>:*, newest activity first) and the workspaces other people have granted it.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
load_contexton 1 other serverreads or searches
“Load your bootstrap context deterministically — pulls L0 (identity) + L1 (architecture) + latest L2 (state) + latest L3 (session summary).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
10 inputs
- top_k_per_layerinteger“Max facts to return per layer (default 10)”
- agent_idstring“Calling agent's identity slug (e.g.”
- profilestring“Optional profile slug (e.g.”
- scopestring“Optional project/tenant-scope prefix (e.g.”
- varsobject“Variable substitutions for the recipe (e.g.”
- max_fact_charsinteger“Per-fact body cap.”
- max_total_charsinteger“Total bundle cap.”
- fullboolean“Return the full (uncapped, 32KB) bundle via the complete compose path.”
- hintstring“Ambient query for the baton section: what this session is about before the user has said anything (e.g.”
- sectionstring“Expand one section of the wake index: every pointer (key — headline) in that key family, ranked permanent → active → newest.”
mark_salientcreates or changes datadescribed as changing data
“Salience peptide — temporarily boost a fact's retrieval ranking because it matters RIGHT NOW: an approaching deadline, a live incident, the topic under active work.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
4 inputs, 1 required
- fact_idstring“UUID of the fact to mark salient (from search results).”
- keystring“Exact fact key — marks the current version.”
- weightnumber“Salience strength 0-3 (default 1).”
- reasonstringrequired“REQUIRED.”
move_factcreates or changes datadescribed as changing data
“Move a fact to a different namespace or layer without changing its content.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
3 inputs, 1 required
- fact_idstringrequired“The UUID of the fact to move”
- new_namespacestring“New namespace (e.g.”
- new_layerinteger“New layer: 0=identity, 1=architecture, 2=state, 3=session.”
reinforce_factcreates or changes datadescribed as changing data
“Reward peptide — reinforce a fact whose recall LED TO A REAL GOOD OUTCOME (fix worked, deploy green, user approved).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
4 inputs, 1 required
- fact_idstring“UUID of the fact to reinforce (from search results).”
- keystring“Exact fact key — reinforces the current version.”
- weightnumber“Reward strength 0-3 (default 1).”
- reasonstringrequired“REQUIRED.”
resume_sessionreads or searches
“Call to load session continuity.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
Takes no inputs.
revoke_granton 1 other serverdeletesdescribed as changing data
“Revoke a pending invitation or active grant as the GRANTOR (owner of the shared namespace).”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
1 input, 1 required
- grant_idstringrequired“UUID of the grant to revoke.”
search_contexton 6 other serversreads or searches
“Search across ingested conversations and session history for broader context.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 1 required
- querystringrequired“Natural language search query”
- top_kinteger“Number of results (default 20, max 100)”
- sourcestring“Filter by source: 'chatgpt' or 'claude'”
- days_backinteger“Only search within last N days”
search_factson 5 other serversreads or searches
“Search your persistent memory for stored facts.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
7 inputs, 1 required
- querystringrequired“What to search for”
- categorystring“Filter by category”
- top_kinteger“Number of results”
- namespacestring“Filter results to a specific namespace.”
- layerinteger“Context persistence layer: 0=identity, 1=architecture, 2=state, 3=session.”
- boost_recentboolean“When true (default), appends the 5 most recent facts for recency signal.”
- recollectboolean“When true (default), appends a RECOLLECTIONS section: facts cross-referenced from the top hits via related_facts and [[wiki]] links, ranked by association stre…”
setup_accountcreates or changes datadescribed as changing data
“Set up or restore your persistent memory connection.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
5 inputs, 1 required
- modestringrequired“'link_or_create' = primary path — user provides email, server handles new vs returning.”
- api_keystring“API key from a previous session (required for mode='restore')”
- emailstring“Email address.”
- codestring“6-digit verification code from email (required for mode='verify').”
- agent_idstring“Optional: bind a sticky agent identity (e.g.”
store_factcreates or changes datadescribed as changing data
“Store information that should persist across sessions.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
7 inputs, 2 required
- textstringrequired“The fact to store”
- categorystringrequired“Fact category”
- is_permanentboolean“Whether this fact should bypass temporal decay”
- namespacestring“Optional namespace to organise facts (e.g.”
- keystring“Named key for this fact.”
- layerinteger“Context persistence layer: 0=identity/stable, 1=architecture/monthly, 2=state/weekly, 3=session/daily.”
- related_factsarray“Optional list of related fact UUIDs to link (knowledge graph edges)”
store_factscreates or changes datadescribed as changing data
“Store up to 50 facts in one call — the same fields as store_fact per item.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
1 input, 1 required
- factsarrayrequired
store_session_summarycreates or changes datadescribed as changing data
“Store a compressed summary of this session to preserve continuity for the next one.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
6 inputs, 1 required
- summarystringrequired“What happened this session — decisions made, work done, context established”
- decisionsstring“Key decisions made or conclusions reached”
- next_stepsstring“What's pending, open questions, what to pick up next session”
- session_idstring“Optional client identifier to scope this summary: 'claude-code', 'cursor', 'claude-chat', 'openclaw'.”
- contributorsarray“Optional list of contributor IDs when multiple agents or users collaborated this session (e.g.”
- scopestring“Optional project slug for project-scoped last-wake-epoch watermark (conventions/wake-rehydration-v2:current).”
switch_workspaceon 6 other serverscreates or changes datadescribed as changing data
“Narrow this session's memory to one project: name='<slug>' scopes recall, the wake bundle, self-notes and the default namespace for new facts to project:<slug>:* (identity and conventions always ride…”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
1 input, 1 required
- namestringrequired“Project slug (the <slug> in project:<slug>:*), or '' to widen.”
wake_statuson 1 other serverreads or searches
“Check which context layers loaded successfully on this session start.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
- agent_idstring“Calling agent's identity slug (e.g.”
- profilestring“Optional profile slug to validate REQUIRE keys against (e.g.”
- scopestring“Optional project/tenant-scope prefix (e.g.”
- varsobject“Variable substitutions for the recipe (e.g.”
watch_eventsreads or searches
“Long-poll this account's fact-write events instead of re-scanning with since_epoch.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
- prefixstring“Only events whose key starts with this prefix.”
- namespacestring“Only events in this namespace (exact).”
- sincestring“Resume cursor: the next_since of the previous call (a stream id '<ms>-<n>'), '0' for everything retained, or a seq integer.”
- max_wait_snumber“Seconds to wait for the first event (0-25, default 20).”

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 32 tools
Says what it returns: 53% of 32 tools
States limits, defaults or errors: 12% of 25 tools
Says when to use it: 60% of 20 tools
Items covered per tool: 2.2 of 4 on average

Counted from the listing

Parameters with a description: 99% of 84
Tools with a description: 100% of 32
Typical description length: 459 characters

The tool set

Counted from the listing

Tools: 32
Size of the list: about 9,247 tokens for an agent to load (characters ÷ 4)
Naming: 32 of 32 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 32 of 32 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. 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://mcp.ctxstore.ai/mcp

Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "ctxstore-mcp": {
      "url": "https://mcp.ctxstore.ai/mcp"
    }
  }
}

VS Code · .vscode/mcp.json

{
  "servers": {
    "ctxstore-mcp": {
      "type": "http",
      "url": "https://mcp.ctxstore.ai/mcp"
    }
  }
}

VS Code (command line) · Bash or zsh terminal (macOS, Linux)

code --add-mcp '{"name":"ctxstore-mcp","type":"http","url":"https://mcp.ctxstore.ai/mcp"}'

Claude Code

claude mcp add --transport http ctxstore-mcp https://mcp.ctxstore.ai/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://mcp.ctxstore.ai/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 #6

The 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 mcp.ctxstore.ai/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/ctxstore-ai/ctxstore-mcp	Opens publicly	matches	api.github.com · 2026-10-22

Who made it?

Feature #7 · lineage

Facts about the publisher. We do not turn them into a trust score.

Namespace: ai.ctxstore
GitHub owner: a personal account (ctxstore-ai)

Repository: github.com/ctxstore-ai/ctxstore-mcp
Stars: 0
Repository age: 181–365 days
Last push: 181–365 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 · 2026-10-22; 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 rating

3 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.
Not metCode pushed to the repository in the 90 days before our checkLast push 181-365 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 2026-10-22. 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 ai.ctxstore/ctxstore-mcp

Answered from the data above

Is ai.ctxstore/ctxstore-mcp safe to install?

We do not rate servers as safe or unsafe. 3 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. 16 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Does ai.ctxstore/ctxstore-mcp 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 ai.ctxstore/ctxstore-mcp been security tested?

Partly. 4 of the 15 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security verdict is published before verification.

What can ai.ctxstore/ctxstore-mcp do?

It lists 32 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, create or change data and delete. We did not call any tool, so this describes the text, not the behaviour.

Can ai.ctxstore/ctxstore-mcp change or delete data?

16 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.

Does ai.ctxstore/ctxstore-mcp 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 ai.ctxstore/ctxstore-mcp?

In github.com/ctxstore-ai/ctxstore-mcp, which opens publicly.

Found this page useful?

Anonymous · no sign-in

A 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.MaxFreedomPollard/compartmentCompartmentalso has tools that creates or changes data, deletes, reads or searchescompare with this one
io.github.Lyellr88/marm-mcp-serveralso has tools that creates or changes data, deletes, reads or searchescompare with this one
io.github.varun29ankuS/shodh-memoryalso has tools that creates or changes data, deletes, reads or searchescompare with this one
io.github.qualixar/superlocalmemorySuperLocalMemoryalso has tools that creates or changes data, deletes, reads or searchescompare with this one
io.github.Intina47/context-syncalso has tools that creates or changes data, deletes, reads or searchescompare with this one
io.github.cdeust/hypermnesia-mcpalso has tools that creates or changes data, deletes, reads or searchescompare with this one

Active servers whose topic is also “ai-and-ml” 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

Open without sign-in

It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-10-23

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: exercised
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: exercised

4 exercised11 not run (reason given)3 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 4 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 4

1Inventory
tool-listReads the declared tools, resources and prompts.exercised
2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised
12Hidden content
audience-hidingChecks resources that hide content from the user.exercised
18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.exercised

Not run, with the reason · 11

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
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

Does not apply to this server · 3

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

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
1,399 msConnected after 0 redirects. No credential was sent or needed.
Read the inventory: 32 tools, 1 resource, 0 prompts.
6,754 msFinished: 4 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.

TopicAI-classified

ai-and-ml

AI-classified · 2026-10-23

Pricing modelAI-classified

no value

No value: the AI answer was held back because the quoted text did not clearly support it.

Programming language

Python

api.github.com · 2026-10-23

Hosting type

remote (hosted by the publisher)

registry · 2026-10-23

MCP capability

experimental, resources, tools

our test · 2026-10-23

Transport

streamable HTTP

registry · 2026-10-23

Required credentials

none declared

registry · no declaration is not a guarantee

Package registry

does not apply

remote-only server: no package is shipped, so there is no package registry

Freshness

0–30 days

registry updatedAt · 2026-10-23

Lifecycle status

active

registry · 2026-10-23

License class

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Integrity hash

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Signature / provenance

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Dependency advisories

does not apply

ships no package, so there are no dependencies to audit

Popularity

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Publisher signals

owner: a personal account · repository age: 181–365 days · stars: 0–9

api.github.com · 2026-10-22

Maintenance

slowing (no push for a while)

api.github.com · 2026-10-22

Environment

the publisher's infrastructure

where it runs, from the hosting type

“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. “ai.ctxstore/ctxstore-mcp: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/ai.ctxstore/ctxstore-mcp

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

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/ai.ctxstore/ctxstore-mcp)](https://protocolprobe.com/mcp/servers/ai.ctxstore/ctxstore-mcp)

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