io.github.elephia/elephia
PYPI · ELEPHIA · SCANNED SEP 20
Git for your AI's context: local-first, deterministic memory over MCP. An elephant never forgets.
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 Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
- 0 of 5 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency19
- Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 95 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability80
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 903 tokens (~75/item across 12 items; 12 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
- Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage89
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 67% of tool parameters carry a description.Partial
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "merge_log" implies "merge" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
How do I install the io.github.elephia/elephia MCP server?
io.github.elephia/elephia runs locally as a PyPI package, launched with uvx elephia. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · elephia
claude mcp add elephia-elephia -- uvx elephia
{
"mcpServers": {
"elephia-elephia": {
"command": "uvx",
"args": [
"elephia"
]
}
}
} {
"servers": {
"elephia-elephia": {
"command": "uvx",
"args": [
"elephia"
]
}
}
} codex mcp add elephia-elephia -- uvx elephia
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"elephia-elephia": {
"type": "local",
"command": [
"uvx",
"elephia"
],
"enabled": true
}
}
} openclaw mcp add elephia-elephia --command uvx --arg elephia
mcp_servers:
elephia-elephia:
command: "uvx"
args: ["elephia"] {
"McpServers": {
"elephia-elephia": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"elephia"
]
}
}
} assistant mcp add elephia-elephia -t stdio -c uvx -a elephia
{
"mcpServers": {
"elephia-elephia": {
"command": "uvx",
"args": [
"elephia"
]
}
}
} 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.
- 20 Sept 26 −2
- Stability: pass → 0.83 functional
- 19 Sept 26 0
- Stability: 0.97 → pass security
- 18 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Sept 26 +15
- Malware scan: unverified → pass ▲ security
- 14 Sept 26 −14
- Malware scan: pass → unverified ▼ security
- 12 Sept 26 −3
- Stability: pass → 0.77 functional
- 11 Sept 26 0
- Stability: 0.97 → pass security
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 20 Sept 2026 · Analysed pypi/elephia@0.2.0
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 →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | setuptools.build_meta |
Background: Why install scripts are a supply-chain risk →
Dependencies 5 packages
| Packages resolved | 5 |
|---|---|
| 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 →
commit_turn ~82
Commit a completed conversation turn (user prompt + assistant answer) to the append-only journal. Durable phrasing ('remember that', 'from now on', corrections, decisions) is automatically merged into the versioned memory wiki. Call after each substantive answer.
| Name | Type | Req | Description |
|---|---|---|---|
| assistant_answer | string | yes | – |
| conversation_id | string | – | – |
| user_prompt | string | yes | – |
No output schema declared.
No examples provided.
context_log ~41
Recent journaled events, newest first (like `git log` for the user's context).
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Max events to return (default 20). |
No output schema declared.
No examples provided.
context_stats ~41
Token accounting and store status: compilations run, patch tokens served, tokens saved vs. sending full history, savings percentage, per-day breakdown, and store counts.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
explain_selection ~75
Explain why each context item was selected or excluded for a prompt: per-item salience scores (frequency, recency, relevance, correction priority, staleness) and exclusion reasons. Use when the user asks 'why did/didn't you remember X?'.
| Name | Type | Req | Description |
|---|---|---|---|
| budget | integer | – | – |
| prompt | string | yes | – |
No output schema declared.
No examples provided.
full_context ~70
Page through the complete raw history (all events plus all wiki pages) when the compact patch is not enough. Returns total token counts so cost is visible before loading more.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Max events to return (default 50). |
| offset | integer | – | Event offset (default 0). |
No output schema declared.
No examples provided.
mark_stale ~68
Mark a memory wiki page as stale/superseded so it is excluded from future context. Use when the user says a saved fact is outdated or wrong.
| Name | Type | Req | Description |
|---|---|---|---|
| page | string | yes | Wiki page title to mark stale. |
| superseded_by | string | – | What replaces it (optional). |
No output schema declared.
No examples provided.
merge_log ~60
The merge history of durable memory: every save/promote/mark_stale/reject mutation, plus the pending-merge queue awaiting review (like `git log` for memory merges).
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Max mutations to return (default 20). |
No output schema declared.
No examples provided.
prepare_context ~109
Compile a compact, token-budgeted context patch from the user's durable memory, ranked by relevance to the prompt. Call this at the start of a conversation or when the topic shifts. Returns the rendered context plus token accounting (patch tokens vs. full-history tokens saved).
| Name | Type | Req | Description |
|---|---|---|---|
| budget | integer | – | Max tokens for the compiled patch (default: server budget). |
| conversation_id | string | – | Stable id for this conversation (default 'default'). |
| prompt | string | yes | The user's current prompt or topic. |
No output schema declared.
No examples provided.
remember ~76
Explicitly save a durable fact to the user's memory wiki. Use when the user asks to remember something or states a lasting preference, decision, or correction.
| Name | Type | Req | Description |
|---|---|---|---|
| fact | string | yes | The fact to save (kept verbatim, max 300 chars). |
| page | string | – | Target wiki page title (optional; inferred when omitted). |
No output schema declared.
No examples provided.
resolve_pending ~47
Approve (merge into durable memory) or reject a pending merge item by its exact content.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | – |
| content | string | yes | Exact content of the pending item. |
No output schema declared.
No examples provided.
search_context ~52
Full-text (BM25) search over all journaled events and memory wiki pages. Returns refs usable with show_context.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Max results (default 8). |
| query | string | yes | – |
No output schema declared.
No examples provided.
show_context ~72
Show one record in full by ref: 'event:<id>' (a journaled turn), 'wiki:<title>' (a memory page with its version history), or 'mut:<id>' (a merge mutation).
| Name | Type | Req | Description |
|---|---|---|---|
| ref | string | yes | event:<id> | wiki:<title> | mut:<id> |
No output schema declared.
No examples provided.
What is the io.github.elephia/elephia MCP server?
io.github.elephia/elephia is an MCP server listed in the public MCP registry as io.github.elephia/elephia. Git for your AI's context: local-first, deterministic memory over MCP. An elephant never forgets. This page covers its PyPI package (elephia).
Is the io.github.elephia/elephia MCP server safe to use?
io.github.elephia/elephia scores 74 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 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.elephia/elephia MCP server expose?
io.github.elephia/elephia exposes 12 tools: prepare_context, commit_turn, remember, mark_stale, search_context, and 7 more. Their descriptions and schemas cost roughly 793 tokens of context every time the server is loaded.
Is the io.github.elephia/elephia MCP server still maintained?
io.github.elephia/elephia is still listed as active in the MCP registry. We last reached this channel on 20 September 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 io.github.elephia/elephia MCP server under?
io.github.elephia/elephia declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.