mitosis
Server Details
Mitosis agent-memory platform: pricing, docs search, platform status, agent skills. No auth.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- Mitosis Labs
TDQS
Scored across 24 tools
Several tools overlap heavily: cortex_ask, search, and cortex_recall all query the same private memory with subtly different retrieval strategies, and fetch is a fourth read path. The goal-lifecycle tools (create/answer/accept/list goals plus choose_enrichment) are staged and distinct but easy to confuse, and cortex_manifest vs cortex_status vs cortex_connectable_sources form another cluster with unclear boundaries. Descriptions do help, but an agent must read carefully to pick correctly.
Names are uniformly snake_case with a verb_noun shape (cortex_create_goal, audiograph_read_received, list_skills). The main deviations are the unprefixed bare verbs search and fetch, and the split between get_pricing/get_platform_status and cortex_* prefixes, which makes it slightly harder to see the grouping.
24 tools is at the heavy end for a memory/knowledge server, and a meaningful chunk is niche (five goal-lifecycle tools, four Audiograph tools, pricing/status/skills). It is defensible given the breadth of the product, but the count feels inflated by overlapping search variants.
The surface covers the full memory lifecycle — ingest, retrieval (three flavors), remember, goals, source connection, and health — plus Audiograph integration and docs. Gaps are minor: there is no way to delete or forget a memory/fact, no tool to remove or disconnect a source or unsubscribe a skill's schedule.
Available Tools
24 toolsaudiograph_list_receivedList Audiographs sent to meARead-onlyIdempotentInspect
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.
Inputs: no named parameters.
audiograph_open_linkOpen an Audiograph linkAIdempotentInspect
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.
Inputs: url (required), recording_id.
audiograph_read_receivedRead an Audiograph sent to meARead-onlyIdempotentInspect
Read one Audiograph someone sent the person you are working with: transcript, notes and who was mentioned. recording_id comes from audiograph_list_received.
Inputs: recording_id (required).
audiograph_task_reportReport on an Audiograph taskAInspect
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.
Inputs: token (required), status (required), report_url (required), step, +4 more.
cortex_accept_goalSave a settled goalAIdempotentInspect
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.
Inputs: draft_id (required).
cortex_answer_goalRecord the user's answer about a goalAIdempotentInspect
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.
Inputs: answers (required), draft_id (required).
cortex_askSearch the user’s memoryARead-onlyIdempotentInspect
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.
Inputs: question (required), limit, since, until, +1 more.
cortex_choose_enrichmentRecord what the user wants pulled out of a sourceAIdempotentInspect
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.
Inputs: feed_key (required), goal, choice, goal_ids, +1 more.
cortex_connectable_sourcesSources this memory could connectARead-onlyIdempotentInspect
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.
Inputs: no named parameters.
cortex_connect_linkConnect link for one sourceARead-onlyIdempotentInspect
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.
Inputs: source_id (required), link_text.
cortex_create_goalDesign a new goal with the userAInspect
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.
Inputs: goal (required), feed_keys.
cortex_ingestAdd a document to the user’s memoryAIdempotentInspect
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).
Inputs: feed, files, title, content, +1 more.
cortex_ingest_conversationSave a conversation into the user’s memoryAIdempotentInspect
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.
Inputs: turns (required), title, session_id.
cortex_list_goalsList saved goals for this memoryARead-onlyIdempotentInspect
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.
Inputs: no named parameters.
cortex_manifestWhat the user’s memory containsARead-onlyIdempotentInspect
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.
Inputs: no named parameters.
cortex_recallSemantic search of the user’s memoryARead-onlyIdempotentInspect
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.
Inputs: query (required), limit.
cortex_rememberSave a fact to the user’s memoryAIdempotentInspect
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.
Inputs: text (required), kind, confidence, source_universal_ids.
cortex_statusMemory freshness and coverageARead-onlyIdempotentInspect
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".
Inputs: no named parameters.
fetchRead one item from the user’s memoryARead-onlyIdempotentInspect
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.
Inputs: id (required). Returns: id, url, text, title, +1 more
get_platform_statusGet platform statusARead-onlyIdempotentInspect
Get the operational status of the Mitosis website, API, and MCP server. Use before reporting an outage or debugging connectivity.
Inputs: service.
get_pricingGet Mitosis pricingARead-onlyIdempotentInspect
Get current Mitosis plans, prices, credit allowances, how usage is charged, and add-ons. Use when comparing costs or recommending a plan.
Inputs: plan.
list_skillsList agent skillsARead-onlyIdempotentInspect
List the agent skills Mitosis publishes (backup create/list/restore/health/diff/schedule/subscribe) with links to each SKILL.md manifest.
Inputs: tag.
searchSearch the user’s memory (deep research)ARead-onlyIdempotentInspect
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.
Inputs: query (required). Returns: results
search_docsSearch Mitosis docsARead-onlyIdempotentInspect
Keyword-search Mitosis documentation and product pages. Returns ranked results with URLs. Use to answer any "how do I…" question about Mitosis.
Inputs: query (required), limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Read-only lookups of public AI agent pricing, free plans and source links. No API key.
Durable memory, headless browser and research for agents. Pay per call: x402 USDC on Base or credits
Public StaffBots plans, industry pages, comparisons, and docs. No auth and no tenant data.
Your company's brain for AI agents. Cited, permission-aware knowledge across every system.
Related MCP Servers
- FlicenseNot gradedqualityAmaintenanceEnables AI agents to search, read, and update a document workspace's knowledge through tools, prompts, and resources, either hosted or self-hosted.-
- AlicenseNot gradedqualityBmaintenanceEnd-to-end agent-managed company brain. Humans and any MCP agent co-author living docs (Markdown + extensions), 40+ visual diagrams (Mermaid, BPMN, D2, PlantUML, ELK, Excalidraw), plans, and a self-learning Knowledge Graph. 163 tools across 16 categories. Auth: OAuth 2.1 or API key. Lean, secure, affordable — from individuals to enterprise.MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to capture, classify, synthesize, and retrieve persistent knowledge through MCP and REST APIs, so multiple agents can share memory and improve across sessions. It provides full-text, semantic, and hybrid search with token-optimized context retrieval from sources like Obsidian, code, transcripts, and terminal sessions.10 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to share persistent memory by ingesting, classifying, synthesizing, and retrieving knowledge through MCP and REST APIs, with token-optimized, tier-aware search and Obsidian sync.10 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.