此 MCP 可以做什么
Provides portable graph-based memory operations for searching, updating, validating, comparing, compacting, and time-filtering knowledge graphs.
功能
工具
6
工具
graph_at_time
Graph At Time
See the memory as it stood on a given day, optionally faded by age. PREMIUM (license).
Relations carrying since and until are filtered to those in force on the
date; with a half-life, confidence decays exponentially with age so a
two-year-old belief does not weigh the same as last week's. Typical input
{"graph": {...}, "as_of": "2026-06-01", "half_life_days": 180} returns
{"as_of": "2026-06-01", "graph": {...}, "dropped": {"not_yet": 1,
"expired": 2}, "decayed": 4}.
Use when the answer depends on when you ask. Not for what changed between
two points - that is graph_diff, which does not need dates at all. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "as_of must be a date like 2026-06-01"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.
只读
幂等
输入模式
{'type': 'object', 'required': ['graph', 'as_of'], 'properties': {'as_of': {'type': 'string', 'description': 'The date to view the memory as of, ISO 8601, e.g. "2026-06-01".'}, 'graph': {'type': 'object', 'description': 'The graph document.', 'additionalProperties': True}, 'half_life_days': {'type': 'integer', 'default': 0, 'minimum': 0, 'description': "Days over which a relation's confidence halves. 0, the\ndefault, disables decay and leaves confidence untouched."}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
graph_compact
Graph Compact
Shrink a memory to the part that still earns its place. PREMIUM (license).
Ranks entities by how connected they are and how much is recorded about
them, keeps anything you name outright, and drops the rest along with the
relations that pointed at them. Typical input {"graph": {...},
"max_entities": 50, "keep": ["Acme Corp"]} returns {"graph": {...},
"kept": 50, "dropped_entities": ["Old Note", ...], "dropped_relations": 12,
"ranking": "degree, then observation count, then name"}.
Use when a graph has outgrown the context you can spend on it. Not for
removing wrong facts - graph_lint finds those, and deleting them is a
decision you should make deliberately rather than by ranking. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.
只读
幂等
输入模式
{'type': 'object', 'required': ['graph'], 'properties': {'keep': {'anyOf': [{'type': 'array', 'items': {'type': 'string'}}, {'type': 'null'}], 'default': None, 'description': 'Entity names to keep regardless of rank, e.g. ["Acme Corp"].\nMatched case-insensitively.'}, 'graph': {'type': 'object', 'description': 'The graph document to compact.', 'additionalProperties': True}, 'max_entities': {'type': 'integer', 'default': 50, 'minimum': 1, 'description': 'How many entities to keep. Default 50.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
graph_diff
Graph Diff
Say exactly what changed between two versions of a memory. FREE.
The audit trail a database gives you for free, without the database.
Typical input {"before": {...}, "after": {...}} returns
{"entities_added": ["Beta Ltd"], "entities_removed": [],
"observations_added": {"Acme Corp": ["renewed in March"]},
"relations_added": [...], "changed": true}.
Use after an upsert to record what a session learned, or between two
agents to see what one knows that the other does not. Not for merging the
two - feed the differences back through graph_upsert for that. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.
只读
幂等
输入模式
{'type': 'object', 'required': ['before', 'after'], 'properties': {'after': {'type': 'object', 'description': 'The later graph document.', 'additionalProperties': True}, 'before': {'type': 'object', 'description': 'The earlier graph document.', 'additionalProperties': True}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
graph_lint
Graph Lint
Find the breaks a memory graph accumulates as it grows. FREE.
Relations pointing at entities that do not exist, entities nothing points
at, near-duplicate names, and observations that contradict each other on
the same entity. Typical input {"graph": {...}} returns {"ok": false,
"dangling_relations": [{"from": "Acme Corp", "to": "Beta Ltd", "missing":
["Beta Ltd"]}], "orphan_entities": ["Old Note"], "near_duplicates":
[["Acme Corp", "Acme Corp."]], "contradictions": []}.
Use before trusting a graph you did not build, or on a schedule as memory
grows. Not for comparing two graphs (graph_diff) and not for shrinking one
(graph_compact). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.
只读
幂等
输入模式
{'type': 'object', 'required': ['graph'], 'properties': {'graph': {'type': 'object', 'description': 'The graph document to check.', 'additionalProperties': True}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
graph_search
Graph Search
Find what the graph knows about something, plus its neighbourhood. FREE.
Scores entities by how many query words appear in the name, type and
observations, then pulls in whatever is within the requested number of
hops - because the useful answer to "what do we know about Acme" is
usually Acme plus who it is connected to. Typical input {"graph": {...},
"query": "acme renewal", "hops": 1} returns {"matches": [{"name": "Acme
Corp", "score": 3, "why": ["name", "observation"]}], "neighbourhood":
{"entities": [...], "relations": [...]}, "hops": 1}.
Use to read memory back before answering. Not for writing (graph_upsert)
and not for narrowing by date, which graph_at_time does. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "query must contain at least one word or number"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.
只读
幂等
输入模式
{'type': 'object', 'required': ['graph', 'query'], 'properties': {'hops': {'type': 'integer', 'default': 1, 'maximum': 3, 'minimum': 0, 'description': 'How far to expand from each match along relations. 0 returns\nmatches only; 3 is the maximum. Default 1.'}, 'graph': {'type': 'object', 'description': 'The graph document to search.', 'additionalProperties': True}, 'limit': {'type': 'integer', 'default': 20, 'maximum': 200, 'minimum': 1, 'description': 'Maximum entities to return. Default 20, maximum 200.'}, 'query': {'type': 'string', 'description': 'Words to look for, e.g. "acme renewal". Matching is on whole\nlowercase words, so it is exact and repeatable rather than fuzzy.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
graph_upsert
Graph Upsert
Fold new facts into a memory graph and get the whole graph back. FREE.
Idempotent by construction: re-adding the same entity, observation or
relation changes nothing, so an agent that replays its own history does not
end up with a graph full of duplicates. Typical input {"graph": {"entities":
[], "relations": []}, "entities": [{"name": "Acme Corp", "type":
"company", "observations": ["renewed in March"]}]} returns {"graph": {...},
"added": {"entities": 1, "observations": 1, "relations": 0}, "merged": 0}.
Use as the single write path for memory. Not for reading it back
selectively - that is graph_search - and not for finding out what a write
changed, which graph_diff answers precisely. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "graph exceeds <value> entities; split it"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.
只读
幂等
输入模式
{'type': 'object', 'properties': {'graph': {'anyOf': [{'type': 'object', 'additionalProperties': True}, {'type': 'null'}], 'default': None, 'description': 'The existing graph document, or omitted to start a new one.\nShape: {"entities": [...], "relations": [...]}.'}, 'entities': {'anyOf': [{'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}}, {'type': 'null'}], 'default': None, 'description': 'Entities to add or extend, each {"name": ..., "type": ...,\n"observations": [...]}. Observations are appended and deduplicated;\nan existing entity keeps its type unless a new one is supplied.'}, 'relations': {'anyOf': [{'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}}, {'type': 'null'}], 'default': None, 'description': 'Relations to add, each {"from": ..., "to": ..., "type":\n..., and optionally "since", "until", "confidence"}. Dates are\nISO 8601 (YYYY-MM-DD); confidence is 0 to 1.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'additionalProperties': True}
历史
近期工具变更
已添加
graph_compact
2026年9月17日 12:36
已添加
graph_at_time
2026年9月17日 12:36
已添加
graph_lint
2026年9月17日 12:36
已添加
graph_diff
2026年9月17日 12:36
已添加
graph_search
2026年9月17日 12:36
已添加
graph_upsert
2026年9月17日 12:36
发现
类似的 MCP 服务器
Stable Baseline
io.stablebaseline/sb
Manages company documents, knowledge graphs, whiteboards, projects, plans, tasks, teams, and improvement workflows.
Dayze — Life Context
com.dayze/life-context
Provides authenticated personal life-context data and tools for contacts, memories, events, expenses, trips, assets, places, and …
YouSpot
com.youspot/youspot
Connects personal contacts, companies, notes, files, CRM records, email, Slack, LinkedIn, and calendars, with search, relationshi…
cypher-mcp
io.github.lonniev/cypher-mcp
Provides named Cypher graph queries and code-orientation tools for tracing capabilities, symbols, invariants, provenance, changes…
mcp
io.nestr/mcp
Manages Nestr workspaces, roles, circles, tensions, governance proposals, comments, daily plans, graph relationships, agents, and…
HiveLearn
io.github.williamechevarria/hivelearn-mcp
Creates and manages courses, lessons, quizzes, enrollments, learning tracks, events, certificates, resources, progress, and commu…
concordance
com.narrowhighway/concordance
Provides deterministic claim verification and audit receipts, along with Bible references, commentary, geography, indexed knowled…
canton-ccpedia
io.github.UnityNodes/canton-ccpedia
Searches and explains Canton Network and Daml documentation, governance proposals, forums, code examples, APIs, releases, and eco…