People Context MCP server
Local-first MCP server giving AI agents contextual knowledge about the people in your life
55 stars267 downloads/wk
Reviews
Write oneNobody has reviewed People Context yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
People Context tools (41, 5 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
add_aliasAdd a normalized-deduplicated alias to an existing person.
add_group_membershipRecord that an existing person held a role in an existing group.
close_group_membershipRecord the last day a historically true membership held.
commit_importCommit accepted people and resolvable interactions idempotently.
complete_reminderTransition one active reminder to completed.
correct_recordCorrect whitelisted assertion fields in place with before/after audit.
create_groupwrite actionCreate one identified group: a class, cohort, team, department, club, household, or community.
explain_shared_connectionsExplain how two people are connected through groups they were both recorded in, and when.
export_dataExport the complete portable domain dataset.
find_connectionReturn one shortest relationship path, or a structured not-connected result.
find_groupsList groups whose normalized name contains `name`, optionally of one `kind`.
forgetHard-delete a person or record and redact identifying audit history.
get_communication_guidanceReturn sensitivity-gated signal for client-composed communication advice.
get_consolidation_contextReturn one person's stored facts, traits, observations, and affiliations and how they relate.
get_groupReturn one group and a bounded page of its recorded memberships.
get_person_contextAssemble a minimal-disclosure context bundle for one person.
get_person_timelineReturn one person's recent history, newest first, as a bounded chronology.
get_relationship_graphReturn active relationship structure around one person, capped for bounded disclosure.
get_sensitive_person_contextReturn context that may include sensitive and restricted records.
get_stale_relationshipsReturn people you have not interacted with recently, using ordinary interactions only.
import_contentExtract and atomically stage header-only candidates from a supported source without bodies.
list_group_membershipsReturn a bounded page of one person's recorded group memberships with each group.
list_remindersList pull-based reminders, due-dated first and communication notes last.
merge_peopleMerge a duplicate person into a primary person atomically.
record_factRecord a time-aware fact about an existing person.
record_interactionRecord a concise interaction summary after validating all participants.
record_observationRecord a subjective observation, separate from disclosed context.
record_traitRecord a derived trait with validated category and provenance.
rememberRecord one thing the user stated about one person, in a single call.
remember_personwrite actionCreate a new person or update the existing one matching `name`.
resolve_personResolve a name, nickname, or partial reference to candidate people.
review_importReturn staged candidates and statuses for one batch.
search_peopleFree-text search over stored people for browsing or lookup.
semantic_searchSearch active people and safe interaction summaries by multilingual semantic similarity.
set_affiliationwrite actionCreate an affiliation, resolving an org id or get/creating by name.
set_communication_philosophyStore communication philosophy verbatim while auditing lengths only.
set_relationshipwrite actionCreate a directed relationship between two existing people.
set_reminderwrite actionCreate a reminder for an existing person.
stage_candidatessupersede_factClose a fact that was true and open its replacement from an effective date.
upcoming_datesReturn ordinary birthdays and dated active reminders inside an inclusive upcoming window.
Public scan report
scanner v0.1.8 · 2026-09-19 · same rubric, same numbers if you re-run it
- Code scan262 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 0 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
What the publisher says
From the People Context repository's README, as published. We do not edit it. Read it on GitHub
people-context
<!-- mcp-name: io.github.JinyangWang27/people-context -->
English | 简体中文
Your agent already remembers your codebase. Now it can remember your people.
people-context is a local-first MCP server and CLI that gives AI agents durable memory about the people in your life: who someone is, how you know them, what you last agreed, and how they like to be talked to. One SQLite file on your machine. No account, no cloud, no network calls.
Why
Ask an assistant "how should I approach Priya about the reporting delay?" and it has nothing: it does not know which Priya, that she is your counterpart at a partner org, that you agreed a new deadline last week, or that she prefers a short email over a call. That knowledge lives in your head, your inbox, and a notes file the agent cannot see.
people-context keeps it in one place the agent can query through narrow tools:
as two candidates with a match reason, never a silent guess.
- Who is this? Explainable name resolution over names, nicknames, aliases, and handles. Two Priyas come back
traits, reminders, and a per-person timeline, each disclosed only as far as the request needs.
- What do I know? Relationships, organisations and roles, durable facts, concise interaction summaries,
and your own written philosophy.
- How do I talk to them? Communication guidance grounded in recorded traits, past friction, open follow-ups,
reviewable candidates. You approve what gets recorded; raw source content is never kept.
- Who has gone quiet? Stale-relationship and upcoming-date reports over what is already stored.
- Get data in safely. Email, mbox, vCard, calendar, LinkedIn, Outlook, and WhatsApp exports are staged as
It is opinionated about trust: writes are audited, forget is a real delete, sensitive records sit behind an operator-only gate that a prompt cannot open, and ordinary commands never touch the network.
Demo
A packaged fictional dataset is the fastest way to see identity resolution, graph traversal, and bounded context without touching real data:
uvx --from people-context pctx demo --resetThe demo always writes its own dedicated database at {XDGDATAHOME or ~/.local/share}/people-context/demo.db. It ignores --db, PEOPLECONTEXTDB, the config file, and workspace discovery, and --reset replaces only that file plus its -wal/-shm companions, so a real database is never read or modified. Seeding writes audited fictional people, handles, affiliations, facts, interactions, and a connected relationship graph, then prints the path-targeted server command and concrete tool calls that use the ids it just created:
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Install directly
claude mcp add people-context -- uvx people-context
People Context: common questions
- Is People Context MCP server safe?
- Yes, by our scan: it is graded A (92/100). Read the People Context safety report
- How do I install People Context?
- It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
- Does People Context need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is People Context maintained?
- The last commit was in the last day (2026-09-19). The latest release is v1.2.1.