io.github.Mars-proj/verifiable-memory
PYPI · VERIFIABLE-MEMORY-MCP · SCANNED SEP 21
Memory for AI agents that can't hallucinate — cited or abstains, provable forget, deterministic.
Available components
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 Security88
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Install-script risk not yet assessed.Unverified
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency6
- Repository check failed: no source repository is declared. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: the license (MIT License) isn't a recognized OSI-approved license. See how to fix → Fail
- Actively maintained (last published 97 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability67
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 713 tokens (~54/item across 13 items; 13 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management93
- Stability observed for 28 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage67
- 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
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
- Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
How do I install the io.github.Mars-proj/verifiable-memory MCP server?
io.github.Mars-proj/verifiable-memory runs locally as a PyPI package, launched with uvx verifiable-memory-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · verifiable-memory-mcp
claude mcp add mars-proj-verifiable-memory -- uvx verifiable-memory-mcp
{
"mcpServers": {
"mars-proj-verifiable-memory": {
"command": "uvx",
"args": [
"verifiable-memory-mcp"
]
}
}
} {
"servers": {
"mars-proj-verifiable-memory": {
"command": "uvx",
"args": [
"verifiable-memory-mcp"
]
}
}
} codex mcp add mars-proj-verifiable-memory -- uvx verifiable-memory-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"mars-proj-verifiable-memory": {
"type": "local",
"command": [
"uvx",
"verifiable-memory-mcp"
],
"enabled": true
}
}
} openclaw mcp add mars-proj-verifiable-memory --command uvx --arg verifiable-memory-mcp
mcp_servers:
mars-proj-verifiable-memory:
command: "uvx"
args: ["verifiable-memory-mcp"] {
"McpServers": {
"mars-proj-verifiable-memory": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"verifiable-memory-mcp"
]
}
}
} assistant mcp add mars-proj-verifiable-memory -t stdio -c uvx -a verifiable-memory-mcp
{
"mcpServers": {
"mars-proj-verifiable-memory": {
"command": "uvx",
"args": [
"verifiable-memory-mcp"
]
}
}
} 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.
- 21 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 19 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Sept 26 +15
- Malware scan: unverified → pass ▲ security
- 17 Sept 26 −3
- Stability: pass → 0.80 functional
- 16 Sept 26 +1
- Stability: 0.97 → pass security
- 15 Sept 26 −15
- Malware scan: pass → unverified ▼ security
- 14 Sept 26 +16
- Malware scan: unverified → pass ▲ security
- 12 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 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 21 Sept 2026 · Analysed pypi/verifiable-memory-mcp@0.1.2
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
Background: How many MCP packages publish verified provenance →
Dependencies 0 packages
| Packages resolved | 0 |
|---|---|
| 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 →
all_paths ~46
All exact fact-paths between start and end entities (each path citable).
| Name | Type | Req | Description |
|---|---|---|---|
| end | string | yes | – |
| max_depth | number | – | – |
| start | string | yes | – |
No output schema declared.
No examples provided.
contradictions ~70
Audit knowledge for conflicts: for functional relations (one value expected, e.g. 'capital','birthdate') return any (subject,relation) holding >1 live value, showing BOTH sources — call before trusting facts that may have been updated or come from multiple sources.
| Name | Type | Req | Description |
|---|---|---|---|
| functional_relations | array | yes | – |
No output schema declared.
No examples provided.
forget ~84
Permanently and PROVABLY delete a stored fact (GDPR / right-to-be-forgotten). Use when the user asks to forget or remove information — the fact is fully erased and you get a signed proof of deletion. object optional (omit to delete all values).
| Name | Type | Req | Description |
|---|---|---|---|
| object | string | – | – |
| relation | string | yes | – |
| subject | string | yes | – |
No output schema declared.
No examples provided.
history ~44
Full life-line of a fact (all versions live+closed, with sources and valid-time). Audit/compliance.
| Name | Type | Req | Description |
|---|---|---|---|
| relation | string | yes | – |
| subject | string | yes | – |
No output schema declared.
No examples provided.
knowledge_root ~21
Merkle root committing the entire current knowledge state (one hash).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
learn_fact ~104
Store a fact (subject, relation, object) the agent must recall EXACTLY later, with its source. Call whenever the user states a fact, preference, decision, name, number, or rule worth remembering — it persists across sessions and is never silently distorted. Optional valid_from for valid-time.
| Name | Type | Req | Description |
|---|---|---|---|
| object | string | yes | – |
| relation | string | yes | – |
| source | string | – | – |
| subject | string | yes | – |
| valid_from | number | – | – |
No output schema declared.
No examples provided.
multihop ~58
Multi-hop chain: start entity + list of relations, follows subject->object each step (exact only, 0% hallucination).
| Name | Type | Req | Description |
|---|---|---|---|
| as_of | number | – | – |
| relations | array | yes | – |
| start | string | yes | – |
No output schema declared.
No examples provided.
prove_fact ~40
Merkle inclusion proof that a fact is in the knowledge state (without revealing other facts).
| Name | Type | Req | Description |
|---|---|---|---|
| relation | string | yes | – |
| subject | string | yes | – |
No output schema declared.
No examples provided.
recall ~87
Look up a stored fact and return the answer WITH its cited source — or an honest 'unknown'. ALWAYS call this before answering a factual or memory question instead of guessing: it returns nothing rather than hallucinating, and includes a signed, verifiable receipt. Optional as_of for valid-time.
| Name | Type | Req | Description |
|---|---|---|---|
| as_of | number | – | – |
| relation | string | yes | – |
| subject | string | yes | – |
No output schema declared.
No examples provided.
stats ~13
Counts + current knowledge root.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
update_fact ~71
Update a fact's value without retraining: closes live versions (valid_to=t) and opens a new one. History is preserved.
| Name | Type | Req | Description |
|---|---|---|---|
| new_object | string | yes | – |
| relation | string | yes | – |
| source | string | – | – |
| subject | string | yes | – |
| t | number | – | – |
No output schema declared.
No examples provided.
verify_proof ~43
Verify a Merkle inclusion proof (leaf, proof, root).
| Name | Type | Req | Description |
|---|---|---|---|
| leaf | string | yes | – |
| proof | array | yes | – |
| root | string | yes | – |
No output schema declared.
No examples provided.
verify_receipt ~32
Verify a signed receipt returned by recall/forget (tamper-evident).
| Name | Type | Req | Description |
|---|---|---|---|
| receipt | object | yes | – |
No output schema declared.
No examples provided.
What is the io.github.Mars-proj/verifiable-memory MCP server?
io.github.Mars-proj/verifiable-memory is an MCP server listed in the public MCP registry as io.github.Mars-proj/verifiable-memory. Memory for AI agents that can't hallucinate, cited or abstains, provable forget, deterministic. This page covers its PyPI package (verifiable-memory-mcp).
Is the io.github.Mars-proj/verifiable-memory MCP server safe to use?
io.github.Mars-proj/verifiable-memory scores 65 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. 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 io.github.Mars-proj/verifiable-memory MCP server expose?
io.github.Mars-proj/verifiable-memory exposes 13 tools: learn_fact, recall, update_fact, history, forget, and 8 more. Their descriptions and schemas cost roughly 713 tokens of context every time the server is loaded.
Is the io.github.Mars-proj/verifiable-memory MCP server still maintained?
io.github.Mars-proj/verifiable-memory is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.