MemoryComb
MCPB · MEMORYCOMB-0.3.2.MCPB
One memory for every AI: Claude, ChatGPT and more share a memory that lives on your computer.
Available components
Last scanned (2 hours ago)
Scores higher than 77% of MCPB 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 Security12
- No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
- Known CVEs were checked across the 31 of 31 dependencies we could resolve, so this covers what we could see, not the whole tree.Partial
- Install-script risk not yet assessed.Unverified
- 1 of 31 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency32
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: the license (Proprietary) isn't a recognized OSI-approved license. See how to fix → Fail
- Actively maintained (last published 19 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability62
- AI-judged instruction clarity (fair).Partial
- Tool/resource definitions use about 820 tokens (~74/item across 11 items; 11 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management70
- Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
- Structured output schemas are declared (27% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
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.
- 5 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.
- 3 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.
- 1 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.
- 30 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.
- 28 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.
- 26 Oct 26 +1
- Package version: 0.3.1 → 0.3.2 functional
- 23 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
- 21 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.
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 mcpb/https://github.com/BryceBlackRoot/memorycomb/releases/download/v0.3.2/memorycomb-0.3.2.mcpb@0.3.2
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | mcpb |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
Dependencies 31 packages
| Packages resolved | 31 |
|---|---|
| No linked repository | 1 |
| 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 →
memory_archive ~36
Retire a memory that is finished or no longer relevant, without a replacement. It stays in history.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | – |
No output schema declared.
No examples provided.
memory_legend ~35
MemoryComb's rules: how memories are labeled, when to search, and what to save or skip. Read once per conversation.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
memory_link ~46
Link two related memories, even across projects, with an optional short note on how they relate.
| Name | Type | Req | Description |
|---|---|---|---|
| a | string | yes | – |
| b | string | yes | – |
| note | – | – | – |
No output schema declared.
No examples provided.
memory_list_cells ~43
List the memories in one project (short summaries only). Use memory_read for full text.
| Name | Type | Req | Description |
|---|---|---|---|
| include_retired | boolean | – | – |
| project | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
memory_list_projects ~24
List every project in the user's MemoryComb with live and retired memory counts.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
memory_read ~30
Read full memories by address, including status, links, and version count.
| Name | Type | Req | Description |
|---|---|---|---|
| addresses | array | yes | – |
No output schema declared.
No examples provided.
memory_resume ~64
Continue a project: returns its live constraints, decisions, open tasks and facts in priority order, plus a receipt of what was read and what was skipped. Call this FIRST whenever the user continues earlier work.
| Name | Type | Req | Description |
|---|---|---|---|
| budget_chars | integer | – | – |
| project | string | yes | – |
No output schema declared.
No examples provided.
memory_review ~100
Fact-check mode: your verdict on a memory ANOTHER AI wrote (memory_resume lists them under fact_check). agree or dispute only when you actually know; otherwise unsure. For a dispute, add the right fact as correction if you know it. The user settles disputes; the AI Scorecard counts real catches and false alarms.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | – |
| correction | – | – | – |
| reason | string | yes | – |
| verdict | string | yes | – |
No output schema declared.
No examples provided.
memory_save ~130
Save ONE durable item (300 chars max): a decision (+ reason), constraint, lasting fact, or open task. Don't save small talk, one-off questions, unpicked options, unconfirmed claims, or secrets. If it returns possible_conflict, ask the user once: keep old, keep new (memory_supersede), or both (force_new).
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | yes | – |
| force_new | boolean | – | – |
| gist | – | – | – |
| project | string | yes | – |
| subject | string | yes | – |
| type | string | yes | – |
| user_stated | boolean | – | – |
No output schema declared.
No examples provided.
memory_search ~67
Keyword search across the user's MemoryComb (or one project). Returns matching memories and a receipt. If nothing matches, tell the user plainly rather than guessing.
| Name | Type | Req | Description |
|---|---|---|---|
| include_retired | boolean | – | – |
| limit | integer | – | – |
| project | – | – | – |
| query | string | yes | – |
No output schema declared.
No examples provided.
memory_supersede ~135
Replace a memory that is no longer true. The old memory retires (kept in history), and the new one goes live. reason="wrong": the old cell was never true (an AI got it wrong); this counts against the AI that wrote it. reason="changed": it was true, but things changed (the user changed a decision, a plan moved on); no penalty. When unsure, ask the user which it was.
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | yes | – |
| gist | – | – | – |
| old_address | string | yes | – |
| reason | string | yes | – |
| user_stated | boolean | – | – |
No output schema declared.
No examples provided.
How do I install the MemoryComb MCP server?
MemoryComb ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, 526da518bbb7330a4ab8d03ed5cfaa572fc56a690ad8ba628a2c7c23f96bf43d; the commands to do that are on this page. If it does not match, do not open it.
mcpb · memorycomb-0.3.2.mcpb
Download bundleCheck the download matches the SHA-256 the MCP registry declares before you open it. If it does not match, do not open the file.
SHA-256
526da518bbb7330a4ab8d03ed5cfaa572fc56a690ad8ba628a2c7c23f96bf43d
macOS / Linux
echo "526da518bbb7330a4ab8d03ed5cfaa572fc56a690ad8ba628a2c7c23f96bf43d memorycomb-0.3.2.mcpb" | shasum -a 256 -c
Windows (PowerShell)
(Get-FileHash -Algorithm SHA256 .\memorycomb-0.3.2.mcpb).Hash -eq "526da518bbb7330a4ab8d03ed5cfaa572fc56a690ad8ba628a2c7c23f96bf43d"
Run it in the folder you saved the bundle to, then open the file with an MCPB-capable host such as Claude Desktop.
What is the MemoryComb MCP server?
MemoryComb is an MCP server listed in the public MCP registry as io.github.BryceBlackRoot/memorycomb. One memory for every AI: Claude, ChatGPT and more share a memory that lives on your computer. This page covers its MCPB bundle (https://github.com/BryceBlackRoot/memorycomb/releases/download/v0.3.2/memorycomb-0.3.2.mcpb).
Is the MemoryComb MCP server safe to use?
MemoryComb scores 47 out of 100 on VerifyMCP. 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.
What tools does the MemoryComb MCP server expose?
MemoryComb exposes 11 tools: memory_legend, memory_list_projects, memory_list_cells, memory_resume, memory_search, and 6 more. Their descriptions and schemas cost roughly 710 tokens of context every time the server is loaded.
What licence is the MemoryComb MCP server under?
MemoryComb declares the Proprietary licence, which is not on the OSI-approved list. Read the terms before using it at work, and note this covers the source only, not the cost of any service it calls.