mitosis MCP server
ai.mitosislabs/mitosismitosislabs.aistreamable-httpv1.0.0Scanned
Mitosis agent-memory platform: pricing, docs search, platform status, agent skills. No auth.
24 tools: 13 change things and 11 only read.
- Reads private data · 5
- Reads text others write · 5
- Can send data out · 1
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
13 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the mitosis MCP server can do
The mitosis MCP server is published by mitosislabs.ai, a domain the MCP Registry verified. It has 24 tools. It can create or change data (13 tools: cortex_recall, cortex_manifest, cortex_connectable_sources, cortex_connect_link and 9 more), but cannot delete data. 11 tools only read.
5 tools read private data (cortex_ask, search, audiograph_list_received and 2 more); 5 tools bring in text other people can write (cortex_ask, search, audiograph_open_link and 2 more); 1 tool can send data out of your system (audiograph_open_link). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 2 findings (annotation-conflict and credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 10, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
24 tools
Changes things 13Claude Code: ask
audiograph_open_linkOpen an Audiograph link someone shared (https://audiograph.si/a/...) for the person you are working with, and read it: the recorded conversation’s transcript, its notes (summary, a…Reads text others writeCan send data outNo findings
Why it is in this group
- The name "audiograph_open_link" says "open": a word for a change.
What it can reach
- untrusted-inputThe description's first sentence says "open" and "http": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Open an Audiograph link someone shared (https://audiograph.si/a/...) for the person you are working with, and read it: the recorded conversation’s transcript, its notes (summary, action items, decisions) and the people and places mentioned. Works for one Audiograph, several sent together, or a MindShare invite. Opening it adds it to their Audiograph library, the same as tapping the link on their iPhone. Long transcripts are cut off; pass recording_id to read one in full.
Annotations the server declares
- title: Open an Audiograph link
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
audiograph_task_reportTell your person how a to-do they handed you from Audiograph is going.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Tell your person how a to-do they handed you from Audiograph is going. Use the report URL and token from the brief. status: "started" when you begin, "working" with a short step, "needs_you" with the question when you need an answer (their phone is notified), "done" with result.summary (and links to what you made or sent) when finished. A done with nothing to show is refused. For a routine, use its runs URL; each run is reported on its own day.
Annotations the server declares
- title: Report on an Audiograph task
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
cortex_accept_goalSaves a settled goal into the memory's goal library, along with the recipe it was designed with, and returns its goal id.No findings
Why it is in this group
- The description's first verb is "save": a word for a change.
Description, as the server wrote it Saves a settled goal into the memory's goal library, along with the recipe it was designed with, and returns its goal id. Still extracts nothing: cortex_choose_enrichment with choice=describe_goal and that id in goal_ids is what runs it on a source.
Annotations the server declares
- title: Save a settled goal
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
cortex_answer_goalRecords the user's answer to the questions from cortex_create_goal, keyed by question id.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Records the user's answer to the questions from cortex_create_goal, keyed by question id. `{"*":"skip"}` is the answer for a user who says to go ahead with whatever Mitosis thinks best. This is the last round: the reply carries answer_required=false and no further questions, because Mitosis asks about a goal once.
Annotations the server declares
- title: Record the user's answer about a goal
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
cortex_choose_enrichmentRecord what the user wants Mitosis to pull out of a data source.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Record what the user wants Mitosis to pull out of a data source. A newly saved source WAITS: it is stored and searchable, but nothing is extracted from it until the user answers. When any save/ingest result carries `choice.choice_required: true`, ask the user its `question` and present EXACTLY two options: "Standard" (Mitosis extracts the people, companies, projects, topics, dates, and how they connect) or "Describe your goal" (the user says what they want extracted). Then call this tool with their answer. Never choose for the user and never infer an answer from silence. After cortex_list_goals, pass `goal_ids` to run those saved recipes on this source now. A brand-new goal is enough: Cortex writes the extract contract and starts extracting. Call it without `choice` to read the current state.
Annotations the server declares
- title: Record what the user wants pulled out of a source
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
cortex_connect_linkThe connect link for one memory source, by id — email and calendar (google-workspace), WhatsApp chats, GitHub, Notion, or file uploads.1 finding
Why it is in this group
- The name "cortex_connect_link" says "link": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "cortex_connect_link" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "cortex_connect_link" says "link": a word for a change.
Description, as the server wrote it The connect link for one memory source, by id — email and calendar (google-workspace), WhatsApp chats, GitHub, Notion, or file uploads. Returns the canonical mitosislabs.ai dashboard page where the user can connect that source to their memory, as a ready markdown link. Source ids appear in `unconnected_sources` on cortex_ask results and in cortex_connectable_sources; which source fits a question is the caller's judgment, made from each entry's `answers` and `tags`. `link_text` names, in the user's own words, what connecting answers — it becomes the connect page's title. Connecting itself is an authorization the user performs on that page; this tool only returns the link.
Annotations the server declares
- title: Connect link for one source
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
cortex_connectable_sourcesWhich sources this memory could connect but hasn't yet — each with what it would make answerable, routing tags, and a connect link for the user.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Which sources this memory could connect but hasn't yet — each with what it would make answerable, routing tags, and a connect link for the user. This is what explains a cortex_ask result that came back empty or off-topic: the source holding that answer is listed here rather than connected. Data connected into this memory stays searchable, cited, and available across every agent and session the user works in.
Annotations the server declares
- title: Sources this memory could connect
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
cortex_create_goalDesigns a goal from the user's own words: what Mitosis should pull out of their data, and how the things in it connect.No findings
Why it is in this group
- The name "cortex_create_goal" says "create": a word for a change.
Description, as the server wrote it Designs a goal from the user's own words: what Mitosis should pull out of their data, and how the things in it connect. Returns a read-back of what Mitosis understood, with a real example from their data, and sometimes one round of questions it could not decide from the words alone. `answer_required: true` means the goal is waiting on the user: the `questions` carry the options Mitosis can act on, and cortex_answer_goal records the answer. `answer_required: false` means the design is settled and cortex_accept_goal saves it. Nothing is extracted from any data here. Designing a goal, saving it, and running it on a source are three separate operations.
Annotations the server declares
- title: Design a new goal with the user
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
cortex_ingestPush a document into this memory so its text becomes searchable.No findings
Why it is in this group
- The description's first verb is "push": a word for a change.
Description, as the server wrote it Push a document into this memory so its text becomes searchable. Pass the file text as content with a filename, or several items in files (each with name and content). Default feed is local_files. The result may carry choice.choice_required: when that is true the source is stored and searchable but waiting for the user to pick Standard or Describe your goal; record that answer with cortex_choose_enrichment. This server cannot read a local filesystem — paths belong on the stdio MCP (mi-cortex-mcp).
Annotations the server declares
- title: Add a document to the user’s memory
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
cortex_ingest_conversationIngest a conversation — the user’s messages and your full answers, verbatim — into the user’s permanent memory, where it becomes searchable and appears in their knowledge graph.1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...connect links, and anything resembling credentials or secrets. Re-ingesting the same sessi..."
Description, as the server wrote it Ingest a conversation — the user’s messages and your full answers, verbatim — into the user’s permanent memory, where it becomes searchable and appears in their knowledge graph. Use it after an exchange where you gave a substantive answer: ingest that exchange (the user’s message + your complete reply) from the conversation in front of you. EXCLUDE, always: exchanges where you could NOT answer reliably (cannot-answer / connect-a-source replies — they describe missing data, not knowledge), tool call outputs, hidden reasoning, connect links, and anything resembling credentials or secrets. Re-ingesting the same session_id updates it instead of duplicating. Split very long conversations across calls.
Annotations the server declares
- title: Save a conversation into the user’s memory
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
cortex_manifestA table of contents for this user's memory: which sources are connected (email, calendar, docs, …), how many items each holds, and the top people, topics and projects.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it A table of contents for this user's memory: which sources are connected (email, calendar, docs, …), how many items each holds, and the top people, topics and projects. It is an index rather than an answer — it contains no message bodies, no dates and no content, so it establishes that a source exists without saying anything about what is in it. The content behind any entry it lists is retrievable with cortex_ask.
Annotations the server declares
- title: What the user’s memory contains
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
cortex_recallSemantic-only vector search over the memory, returning source excerpts.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Semantic-only vector search over the memory, returning source excerpts. Prefer cortex_ask, which also uses full-text and graph expansion; reach for this when you specifically want nearest-neighbour matches on meaning.
Annotations the server declares
- title: Semantic search of the user’s memory
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
cortex_rememberPersist a fact, decision or conclusion into the memory, attributed to you.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Persist a fact, decision or conclusion into the memory, attributed to you. It becomes retrievable via cortex_ask immediately, in this session and every future one, from any agent the user has connected. Provenance: pass source_universal_ids from a previous cortex_ask so the fact links to its evidence. Keep each memory to ONE self-contained fact. Use this whenever the conversation produces a durable conclusion the user would want remembered — a decision, a preference, an outcome, a commitment. If the result carries `choice.choice_required: true`, the memories source is waiting for the user’s enrichment choice: ask `choice.question`, offer exactly "Standard" or "Describe your goal", and record the answer with cortex_choose_enrichment.
Annotations the server declares
- title: Save a fact to the user’s memory
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 11Show 11 read-only tools
audiograph_list_receivedList the Audiographs (recorded conversations) other people have sent the person you are working with: who sent each, its title, date and length.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "audiograph_list_received" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "list" and "conversation": it reads messages.
- untrusted-inputThe description's first sentence says "list" and "conversation": it reads messages, which other people can write.
Description, as the server wrote it List the Audiographs (recorded conversations) other people have sent the person you are working with: who sent each, its title, date and length. Read one with audiograph_read_received.
Annotations the server declares
- title: List Audiographs sent to me
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
audiograph_read_receivedRead one Audiograph someone sent the person you are working with: transcript, notes and who was mentioned.Reads private dataNo findings
Why it is in this group
- The name "audiograph_read_received" says "read": a word for reading.
What it can reach
- private-dataThe description's first sentence says "read" and "note": it reads notes.
Description, as the server wrote it Read one Audiograph someone sent the person you are working with: transcript, notes and who was mentioned. recording_id comes from audiograph_list_received.
Annotations the server declares
- title: Read an Audiograph sent to me
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
cortex_askSearches the user's real, private memory — the email, calendar, files, contacts and notes they have connected, plus facts agents have saved — fusing vector, full-text and graph ret…Reads private dataReads text others writeNo findings
Why it is in this group
- The description's first verb is "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "search" and "email": it reads mail.
- private-dataThe input names a table (input.source_table), and the tool reads: it reads databases.
- untrusted-inputThe description's first sentence says "search" and "email": it reads inbound email, which other people can write.
Description, as the server wrote it Searches the user's real, private memory — the email, calendar, files, contacts and notes they have connected, plus facts agents have saved — fusing vector, full-text and graph retrieval with provenance. This is their current data on their work, schedule, contacts, projects, documents, decisions and history, which training data and session context do not contain. Results include citations (universal ids), freshness, and `cited_graph_url`, a deep link showing the cited nodes highlighted in the user's own graph. A later cortex_remember links to what was retrieved here. Retrieval returns nearest matches rather than a thresholded set, so a question whose answer lives in an unconnected source comes back with the closest thing in the memory instead of with nothing. A `source_gap` object in the result names that case: the memory holds data, but the source that would answer this question is not connected. It lists those sources, what each answers, and one connect link, on `cta`. A `possible_source_gap` object is the conditional form — results exist but may be near-misses rather than an answer. A result carrying neither means the answer is genuinely absent from the memory rather than merely unretrieved.
Annotations the server declares
- title: Search the user’s memory
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
cortex_list_goalsThe saved goals this office already asked Mitosis to pull out of data.No findings
Why it is in this group
- The name "cortex_list_goals" says "list": a word for reading.
Description, as the server wrote it The saved goals this office already asked Mitosis to pull out of data. Call this before choosing enrichment on a new source so you can offer those goals (the user can pick several) instead of inventing a new one. Last-used goals are first. Then pass the chosen ids as goal_ids to cortex_choose_enrichment.
Annotations the server declares
- title: List saved goals for this memory
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
cortex_statusMemory health: per-source ingest and embed counts plus last sync times.No findings
Why it is in this group
- The name "cortex_status" says "status": a word for reading.
Description, as the server wrote it Memory health: per-source ingest and embed counts plus last sync times. Use when you need to know whether the memory is fresh or still ingesting, or when a search came back empty and you need to tell the user whether that means "no data yet" or "nothing matched".
Annotations the server declares
- title: Memory freshness and coverage
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
fetchRetrieve the full contents of a single item from the user’s memory by its id.No findings
Why it is in this group
- The name "fetch" says "fetch": a word for reading.
Description, as the server wrote it Retrieve the full contents of a single item from the user’s memory by its id. Ids come from `search` results. Use this when a search result looks relevant and you need the whole record rather than the excerpt.
Annotations the server declares
- title: Read one item from the user’s memory
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_platform_statusGet the operational status of the Mitosis website, API, and MCP server.Reads text others writeNo findings
Why it is in this group
- The name "get_platform_status" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "get" and "website": it reads web pages, which anyone can write.
Description, as the server wrote it Get the operational status of the Mitosis website, API, and MCP server. Use before reporting an outage or debugging connectivity.
Annotations the server declares
- title: Get platform status
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_pricingGet current Mitosis plans, prices, credit allowances, how usage is charged, and add-ons.No findings
Why it is in this group
- The name "get_pricing" says "get": a word for reading.
Description, as the server wrote it Get current Mitosis plans, prices, credit allowances, how usage is charged, and add-ons. Use when comparing costs or recommending a plan.
Annotations the server declares
- title: Get Mitosis pricing
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_skillsList the agent skills Mitosis publishes (backup create/list/restore/health/diff/schedule/subscribe) with links to each SKILL.md manifest.No findings
Why it is in this group
- The name "list_skills" says "list": a word for reading.
Description, as the server wrote it List the agent skills Mitosis publishes (backup create/list/restore/health/diff/schedule/subscribe) with links to each SKILL.md manifest.
Annotations the server declares
- title: List agent skills
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
searchSearch the user's own private memory — their email, calendar, documents, contacts, chat history and every fact agents have remembered — and return ranked matches with citation ids …Reads private dataReads text others writeNo findings
Why it is in this group
- The name "search" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "search" and "email": it reads mail.
- untrusted-inputThe description's first sentence says "search" and "email": it reads inbound email, which other people can write.
Description, as the server wrote it Search the user's own private memory — their email, calendar, documents, contacts, chat history and every fact agents have remembered — and return ranked matches with citation ids and links. This is their current data on their work, schedule, contacts, projects, documents, decisions and history, which training data and session context do not contain. Pass an id from these results to `fetch` to read the full record.
Annotations the server declares
- title: Search the user’s memory (deep research)
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_docsKeyword-search Mitosis documentation and product pages.Reads private dataNo findings
Why it is in this group
- The name "search_docs" says "search": a word for reading.
What it can reach
- private-dataThe name "search_docs" says "search" and "doc": it reads documents.
Description, as the server wrote it Keyword-search Mitosis documentation and product pages. Returns ranked results with URLs. Use to answer any "how do I…" question about Mitosis.
Annotations the server declares
- title: Search Mitosis docs
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
25 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data5
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write5
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__mitosis__audiograph_open_link"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:26 UTC, unchanged since Nov 6, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 13
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://mitosislabs.ai/.well-known/oauth-protected-resource/api/mcp
- Authorization servers
- https://mitosislabs.ai
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- yes
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 13 tools that change things (13 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mitosislabs.ai/api/mcp: tools/list returned 24 tools to an anonymous client, including cortex_recall (write), cortex_manifest (write), cortex_connectable_sources (write), cortex_connect_link (write), cortex_remember (write) and 8 more
Posture changes
- Nov 6, 2026
- Tools that change things, listed without credentials: 11 to 13
Findings
Matches of fixed checks, with the text they matched.
The server marks "cortex_connect_link" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "cortex_connect_link" says "link": a word for a change.
The description mentions "credentials".
What this check looks forMatched text
description: "...connect links, and anything resembling credentials or secrets. Re-ingesting the same sessi..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools4 added.+4 addedView diff
- Added:audiograph_list_receivedOnly reads
- Added:audiograph_open_linkChanges things
- Added:audiograph_read_receivedOnly reads
- Added:audiograph_task_reportChanges things
PostureRemote posture changed. Tools that change things, listed without credentials: 11 -> 13.View diff
- Tools that change things, listed without credentials: 11 to 13
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http mitosis https://mitosislabs.ai/api/mcpclaude mcp add --transport http mitosis https://mitosislabs.ai/api/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__mitosis__cortex_ask",
"mcp__mitosis__cortex_status",
"mcp__mitosis__cortex_list_goals",
"mcp__mitosis__search",
"mcp__mitosis__fetch",
"mcp__mitosis__audiograph_list_received",
"mcp__mitosis__audiograph_read_received",
"mcp__mitosis__get_pricing",
"mcp__mitosis__get_platform_status",
"mcp__mitosis__search_docs",
"mcp__mitosis__list_skills"
],
"ask": [
"mcp__mitosis__cortex_recall",
"mcp__mitosis__cortex_manifest",
"mcp__mitosis__cortex_connectable_sources",
"mcp__mitosis__cortex_connect_link",
"mcp__mitosis__cortex_remember",
"mcp__mitosis__cortex_ingest",
"mcp__mitosis__cortex_ingest_conversation",
"mcp__mitosis__cortex_create_goal",
"mcp__mitosis__cortex_answer_goal",
"mcp__mitosis__cortex_accept_goal",
"mcp__mitosis__cortex_choose_enrichment",
"mcp__mitosis__audiograph_open_link",
"mcp__mitosis__audiograph_task_report"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as mitosis. Review it before you use it.
Capability tags behind 7 rules
- mcp__mitosis__cortex_ask private-data, untrusted-input
- mcp__mitosis__search private-data, untrusted-input
- mcp__mitosis__audiograph_open_link untrusted-input, outbound
- mcp__mitosis__audiograph_list_received private-data, untrusted-input
- mcp__mitosis__audiograph_read_received private-data
- mcp__mitosis__get_platform_status untrusted-input
- mcp__mitosis__search_docs private-data
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/ai.mitosislabs/mitosis/verify?hash=e7fabcf2d4d74b123e40894fde05bf55c11ec2a56f061826849585b23cc9f474" | jq -e '.changed == false'Pinned hash e7fabcf2d4d7, from Nov 10, 2026, 03:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.mitosislabs/mitosis/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.mitosislabs/mitosis)Source: MCP Registry · repository. Synced Oct 21, 2026, 17:42 UTC.
mitosis MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the mitosis MCP server safe?
- No scan can promise that. What its definitions show: 24 tools, 13 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the mitosis MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the mitosis MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the mitosis MCP server have?
- 24 tools: 13 write, 11 read. cortex_recall, cortex_manifest, cortex_connectable_sources, cortex_connect_link, cortex_remember, cortex_ingest, cortex_ingest_conversation, cortex_create_goal and 16 more.
Does the mitosis MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the mitosis MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): audiograph_open_link.
Has the mitosis MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 10, 2026. Every change is on this page and in its Atom feed.