brain-core
PYPI · BRAIN-CORE-MCP
Memory for a Claude Code agent that survives the session: five tools, a markdown vault, all local.
Available components
Last scanned (3 hours ago)
Scores higher than 47% of PyPI servers
Category Memory and Knowledge
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 3 of 37 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency97
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to xy-claude/brain-core). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 2 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability0
- Schema quality not yet verified: our sandbox could not run this package, so we have no schema to assess.Unverified
Stability & Change Management0
- Stability not yet verified: our sandbox could not run this package, so we have no schema to compare.Unverified
Tool Coverage0
- Tool coverage not yet verified: our sandbox could not run this package, so we have no tool definitions to assess.Unverified
Tool Safety0
- Tool safety not yet verified: our sandbox could not run this package, so we have no tool text to scan.Unverified
Capabilities0
- Protocol version not yet verified: our sandbox could not run this package, so we never saw its MCP handshake.Unverified
Unverified: 5 categories
Categories scored 0 because our sandbox could not run this package, so we have no schema for these checks to read. That is a gap on our side rather than a finding about the package, and we only credit what we can confirm, so the score stands at 0 until we can run it. How we score packages →
Checks we ran (9)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
Checks we could not complete (5)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Schema quality in Schema Quality & AI Usability (scores 0 for this)Schema quality not yet verified: our sandbox could not run this package, so we have no schema to assess.
- Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: our sandbox could not run this package, so we have no schema to compare.
- Tool coverage in Tool Coverage (scores 0 for this)Tool coverage not yet verified: our sandbox could not run this package, so we have no tool definitions to assess.
- Tool safety in Tool Safety (scores 0 for this)Tool safety not yet verified: our sandbox could not run this package, so we have no tool text to scan.
- Capabilities in Capabilities (scores 0 for this)Protocol version not yet verified: our sandbox could not run this package, so we never saw its MCP handshake.
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 3 Nov 26 0
- Package version: 0.4.4 → 0.4.6 functional
- 2 Nov 26 49
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed pypi/brain-core-mcp@0.4.6
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | pypi |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | xy-claude/brain-core |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/xy-claude/brain-core/.github/workflows/release.yml@refs/tags/v0.4.6 |
| Rekor log index | 3652084264 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:16d64355837b47c087cd2f86b2129e089fabbfe12b0d67e76edd0f080ff9e9a3 |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | Known build tool | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 37 packages
| Packages resolved | 37 |
|---|---|
| Stale | 3 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
Tools for package channels are captured by running the package in an isolated sandbox. The most recent sandbox run could not capture a tool list from this package.
How do I install the brain-core MCP server?
brain-core runs locally as a PyPI package, launched with uvx brain-core-mcp serve, plus the required agent_dir, which you supply. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · brain-core-mcp
claude mcp add xy-claude-brain-core -- uvx brain-core-mcp serve
Incomplete: the registry marks agent_dir as required and gives no value we can show, so it is not in this command. Add it before you run it.
What is the brain-core MCP server?
brain-core is an MCP server listed in the public MCP registry as io.github.xy-claude/brain-core. Memory for a Claude Code agent that survives the session: five tools, a markdown vault, all local. This page covers its PyPI package (brain-core-mcp).
Is the brain-core MCP server safe to use?
brain-core scores 49 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
Is the brain-core MCP server still maintained?
brain-core is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the brain-core MCP server under?
brain-core declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the brain-core MCP server?
VerifyMCP ran 9 checks on brain-core, covering Malware scan, Known CVEs, Install scripts, Dependency health and 5 more. 5 items could not be completed, a gap on our side rather than a finding about brain-core: Schema quality, Stability, Tool coverage, Tool safety and 1 more. 5 categories score 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.