GRAFOMEM CGR Capture MCP server
com.grafomem/cgr-capture·v0.1.0·3 starsRecord agent judgments and their real outcomes on GRAFOMEM Cloud. Capture now, score later.
3 stars14 downloads/wk
Reviews
Write oneNobody has reviewed GRAFOMEM CGR Capture yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
GRAFOMEM CGR Capture tools (2)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
cgr_record_decisionRecord a governed dev-loop JUDGMENT (certify/reject) attributed to a
cgr_record_outcomeRecord the resolved OUTCOME for a work_item_id. Maps the result to
Public scan report
scanner v0.1.10 · 2026-10-31 · same rubric, same numbers if you re-run it
- Code scan4 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 qualitystatic API keys via environment variables6/15
- Maintenancelast push 14 days ago15/15
- Maintainer identitynamespace and repository owner differ; website matches verified namespace6/10
How GRAFOMEM CGR Capture compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 80/100
- higher than 60% of 4,460 AI and agents servers
- Tools
- 2
- the typical AI and agents server has 6
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 3
- more than 75% of 2,711 AI and agents servers
- Downloads a week
- 14
- more than 3% of 1,538 AI and agents servers with a package
What its tools let an agent do: 2 read
Install GRAFOMEM CGR Capture in Claude Code, Cursor or VS Code
claude mcp add cgr-capture -- uvx grafomem-cgr
What the publisher says
From the GRAFOMEM CGR Capture repository's README, as published. We do not edit it. Read it on GitHub
GRAFOMEM
The governed memory runtime for agents. Signed checkpoints, provable erasure, portable memory — a drop-in wrapper for your LangGraph checkpointer.
pip install grafomem langgraph-checkpoint-grafomem langgraphfrom typing import TypedDict
from cryptography.hazmat.primitives.asymmetric import ed25519
from langgraph.graph import StateGraph, START, END
from langgraph.checkpoint.memory import MemorySaver
from grafomem_checkpoint import GrafomemSerializer, GrafomemCheckpointSaver
# ── the entire GRAFOMEM integration: an Ed25519 signing key, then wrap ANY
# LangGraph checkpointer. Pass it to compile() as you already do. ──
priv = ed25519.Ed25519PrivateKey.generate()
saver = GrafomemCheckpointSaver(MemorySaver(serde=GrafomemSerializer(private_key=priv)))
# ── your ordinary LangGraph agent ──
class State(TypedDict):
messages: list
def agent(state: State) -> State:
return {"messages": state["messages"] + ["hello from the agent"]}
b = StateGraph(State); b.add_node("agent", agent)
b.add_edge(START, "agent"); b.add_edge("agent", END)
app = b.compile(checkpointer=saver)
cfg = {"configurable": {"thread_id": "user-42"}}
app.invoke({"messages": []}, cfg)
# signed, content-addressed checkpoint
tup = saver.get_tuple(cfg)
print("signed checkpoint hash:", tup.metadata["grafomem_content_hash"])
# cryptographic erasure receipt — proof the erasure transition occurred
saver.delete_thread("usersigned checkpoint hash: ecd0e28938738cc55b3c888f7449503fd586723a699e1d326d74cc0f154874f7
erasure receipt: LangGraphErasureReceipt(pre_state_hash='d9a16ef8…', post_state_hash='0e5751c0…',
scope='user-42', key_id='grafomem_checkpoint', timestamp='2026-…', signature=b'…')(hashes and signature vary per run — each run generates a fresh key)
What just happened: every state transition your agent made was captured as a signed, content-addressed checkpoint — and when you deleted, you got a cryptographic receipt proving the erasure transition occurred. Memory your agents can move, merge, and prove they erased.
Why
Agent memory today is a JSON blob you have to trust. GRAFOMEM makes it evidence: every write signed, every fact content-addressed, every deletion receipted. When someone asks "what did your agent know, and when?" — you answer with proofs, not logs.
Two tiers, one system
- Working memory — fast, bounded context state for the agent loop.
- Durable facts (GMP) — governed, bi-temporal, signed facts with provenance. The GRAFOMEM Memory Protocol is an open spec with an executable conformance suite: a backend's capability counts as supported when it passes the test, not when the vendor says so.
→ Architecture overview
Integrations
- LangGraph — the quickstart above. → docs
- Claude / MCP — expose governed memory as MCP tools. → docs
- Reference server — a REST + MCP server (grafomem[server] extra); a hosted instance runs live at api.grafomem.com. → self-hosting docs
The bigger picture: verify the agent, not just the answer
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
GRAFOMEM CGR Capture: common questions
- Is GRAFOMEM CGR Capture MCP server safe?
- Mostly: it is graded B (80/100). Read the GRAFOMEM CGR Capture safety report
- How do I install GRAFOMEM CGR Capture?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does GRAFOMEM CGR Capture need an API key?
- Yes. The registry entry asks for
GRAFOMEM_CGR_TENANT_KEY. - Is GRAFOMEM CGR Capture maintained?
- The last commit was 18 days ago (2026-10-17). The latest release is v0.1.0.
- What can I use instead of GRAFOMEM CGR Capture?
- Servers from other publishers that do the same job: FireCMS Cloud MCP server, Alibaba Cloud DashScope — Qwen MCP server and Mnemoverse Memory MCP server.
- How does GRAFOMEM CGR Capture compare with other AI and agents MCP servers?
- safety score 80/100 (higher than 60% of 4,460 AI and agents servers); tools 2 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to GRAFOMEM CGR Capture
Same job from other publishers: the closest match first, then the best rated.
- FireCMS CloudManage FireCMS Cloud from an AI agent: Firestore data, collections, schemas and users.not reviewedEstablishedA
- Alibaba Cloud DashScope — QwenAlibaba Cloud DashScope MCP: Qwen chat, embeddings, and model discovery on your own account.not reviewedEstablishedB
- Mnemoverse MemoryHosted agent memory that learns from outcomes, with shared rooms. No key: mcp.mnemoverse.com/mcpnot reviewedEstablishedA
- MockserverMock, record/replay, verify and chaos-test any HTTP, REST, gRPC or LLM dependency over MCP.not reviewedEstablishedA
- CHAP CoordinatorAuditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.not reviewedEstablishedA