Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.leocelis/stele

PYPI · STELE-MCP

Governed agent memory: lessons stay out of search until another actor promotes them with evidence.

Available components

+7 this week 69 Trust /100

Last scanned (13 hours ago)

Scores higher than 62% of PyPI servers

Category Memory and Knowledge

Trust breakdown (7 categories)

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
  • 0 of 29 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency48
  • 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
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 0 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability46
  • AI-judged instruction clarity (poor).Fail
  • Tool/resource definitions use about 1778 tokens (~49/item across 36 items; 36 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management50
  • Stability observed for 15 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 (100% of tools); any adoption earns full credit.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "stele_delete" implies "delete" 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 36 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

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 →

Changelog

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 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 20 Nov 26 +7
    • Malware scan: unverified → pass ▲ security
    • Stability: unverified → 0.47 ▲ functional
    • Package version: 18.16.4 → 18.16.5 functional
  • 18 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 16 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 15 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 12 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 11 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 9 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
Diagnostics

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 Nov 2026 · Analysed pypi/stele-mcp@18.16.5

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi
Reason No attestation published

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 29 packages
Packages resolved 29
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 36 exposed · ~1,778 tokens

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 →

Tool Tokens
stele_add ~37

ADD a distilled structured entry into quarantine. Pass entry as JSON object string.

NameTypeReqDescription
entry_jsonstringyes–
ts–––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_add_batch ~36

Atomic multi-ADD under one lock.

NameTypeReqDescription
actor–––
entries_jsonstringyes–
ts–––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_attach ~60

Content-address bytes (base64); optionally LINK to an entry (FF-6).

NameTypeReqDescription
actorstringyes–
data_base64stringyes–
entry_id–––
kindstring––
ts–––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_belief_at ~59

Bi-temporal point-in-time belief inventory or SEARCH.

NameTypeReqDescription
as_ofstringyes–
budgetinteger––
consumer_scopestringyes–
principal_scopes_json–––
query–––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_conflict_surface ~30

Conflict-preserving contested pairs — no auto-collapse.

NameTypeReqDescription
body_max_charsinteger––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_delete ~54

DELETE by entry_id or subject_id (true erase + index rebuild).

NameTypeReqDescription
actorstringyes–
entry_id–––
reasonstring––
subject_id–––
ts–––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_diff_stores ~36

Diff this store vs another root (e.g. snapshot) by entry id sets.

NameTypeReqDescription
other_rootstringyes–
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_doctor ~27

Operator health report: verify + stats + contested + stale.

NameTypeReqDescription
now–––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_entangled_suspects ~55

Human-review queue for LINK-entangled poison (report only).

NameTypeReqDescription
limitinteger––
seed_ids_json–––
untrusted_agents_json–––
untrusted_sources_json–––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_entry_schema ~24

JSON Schema 2020-12 for Stele entries (interop).

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes–

No examples provided.

stele_export ~73

Export a redacted, audience-tiered pack (storage ≠ pack).

NameTypeReqDescription
audiencestringyes–
created_at–––
deststringyes–
expirystringyes–
purposestringyes–
scopestringyes–
subject_allowlist_json–––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_forget_compliance ~59

Post-erasure active-forgetting probe (GateMem-shaped).

NameTypeReqDescription
consumer_scopestringyes–
entry_ids_json–––
forbidden_substrings_json–––
probe_query–––
subject_id–––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_hydrate ~58

Import a redacted pack (ADD; optional promote with external evidence).

NameTypeReqDescription
actorstringyes–
evidence_json–––
pack_dirstringyes–
promoteboolean––
ts–––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_hygiene_candidates ~42

Zombie / net-harm hygiene report — no auto-delete.

NameTypeReqDescription
limitinteger––
now–––
unused_before–––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_lineage ~31

Supersede chain + journal audit lineage (TOKI-shaped).

NameTypeReqDescription
entry_idstringyes–
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_link ~62

LINK an entry to an artifact, test, entry, or source.

NameTypeReqDescription
actorstringyes–
digest–––
entry_idstringyes–
kindstringyes–
refstringyes–
ts–––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_list ~86

LIST the calling key's store entries in pages: id, layer, title, state, written_at. state: "quarantine" | "promoted" | omitted (all live entries). limit: 1-200 (default 50). cursor: the next_cursor from the previous page.

NameTypeReqDescription
cursor–––
limitinteger––
state–––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_list_contested ~23

List contested entries awaiting evidenced resolution (TECH_SPEC Q5).

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes–

No examples provided.

stele_pin ~47

Pin or unpin a promoted lesson for SEARCH priority.

NameTypeReqDescription
actorstringyes–
entry_idstringyes–
pinnedboolean––
ts–––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_promote ~65

PROMOTE a quarantined entry with external-oracle evidence (JSON array).

NameTypeReqDescription
actorstringyes–
block_injection_suspectsboolean––
entry_idstringyes–
evidence_jsonstringyes–
ts–––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_purge_by_provenance ~70

Provenance recovery: dry-run or purge entries from untrusted source/agent.

NameTypeReqDescription
actorstringyes–
dry_runboolean––
ts–––
untrusted_agents_jsonstring––
untrusted_sources_jsonstring––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_record_outcome ~61

Record helpful/harmful/ignored after using a lesson; helpful refreshes last_verified.

NameTypeReqDescription
actorstringyes–
entry_idstringyes–
note–––
outcomestringyes–
ts–––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_reflect ~44

REFLECT: dedupe, expire, surface conflicts (no auto-resolve).

NameTypeReqDescription
actorstringyes–
stale_before–––
ts–––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_related ~27

Outbound + inbound LINK neighborhood for an entry.

NameTypeReqDescription
entry_idstringyes–
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_resolve_contested ~62

Resolve a contested pair by evidenced supersede — never auto-merge.

NameTypeReqDescription
actorstringyes–
evidence_jsonstringyes–
loser_idstringyes–
ts–––
winner_idstringyes–
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_reverify ~48

Batch-refresh last_verified with external oracle evidence.

NameTypeReqDescription
actorstringyes–
entry_ids_jsonstringyes–
evidence_jsonstringyes–
ts–––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_reviewer_corrections ~39

Bounded contested-first correction slice for reviewer roles.

NameTypeReqDescription
include_contestedboolean––
limitinteger––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_search ~192

SEARCH promoted entries; stale/model policies are flag or withhold.

NameTypeReqDescription
as_of–––
body_max_chars–––
budgetinteger––
consumer_domain–––
consumer_env_json–––
consumer_model_id–––
consumer_scopestringyes–
follow_link_depthinteger––
follow_linksboolean––
include_contestedboolean––
min_weibull–––
model_policystring––
prefer_freshboolean––
prefer_helpfulboolean––
principal_scopes_json–––
querystringyes–
stale_policystring––
trusted_sources_json–––
weibull_etanumber––
weibull_kappanumber––
withhold_injection_suspectsboolean––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_snapshot ~44

Cold-copy SoT (manifest, journal, entries, attachments) to dest.

NameTypeReqDescription
actorstringyes–
deststringyes–
ts–––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_stale_report ~26

List promoted entries past the staleness horizon.

NameTypeReqDescription
now–––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_stats ~26

Store health dashboard: counts by state/layer/scope.

NameTypeReqDescription
now–––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_supersede ~56

SUPERSEDE an old lesson with a new quarantined entry (history kept).

NameTypeReqDescription
actorstringyes–
new_entry_jsonstringyes–
old_idstringyes–
ts–––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_timeline ~24

Journal history for one entry.

NameTypeReqDescription
entry_idstringyes–
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_update ~46

UPDATE non-state fields on an existing entry.

NameTypeReqDescription
actorstringyes–
entry_idstringyes–
patch_jsonstringyes–
ts–––
NameTypeReqDescription
resultstringyes–

No examples provided.

stele_verify ~22

C4 integrity report: dual-location, schema, journal parse.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes–

No examples provided.

stele_verify_pack ~27

Offline pack integrity: stamps + secret scan.

NameTypeReqDescription
pack_dirstringyes–
NameTypeReqDescription
resultstringyes–

No examples provided.

Install

How do I install the io.github.leocelis/stele MCP server?

io.github.leocelis/stele runs locally as a PyPI package, launched with uvx stele-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 · stele-mcp

# add to Claude Code
claude mcp add leocelis-stele -- uvx stele-mcp
Common questions

What is the io.github.leocelis/stele MCP server?

io.github.leocelis/stele is an MCP server listed in the public MCP registry as io.github.leocelis/stele. Governed agent memory: lessons stay out of search until another actor promotes them with evidence. This page covers its PyPI package (stele-mcp).

Is the io.github.leocelis/stele MCP server safe to use?

io.github.leocelis/stele scores 69 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 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.leocelis/stele MCP server expose?

io.github.leocelis/stele exposes 36 tools: stele_add, stele_add_batch, stele_attach, stele_belief_at, stele_conflict_surface, and 31 more. Their descriptions and schemas cost roughly 1,778 tokens of context every time the server is loaded.

Is the io.github.leocelis/stele MCP server still maintained?

io.github.leocelis/stele is still listed as active in the MCP registry. We last reached this channel on 21 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 io.github.leocelis/stele MCP server under?

io.github.leocelis/stele 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 io.github.leocelis/stele MCP server?

VerifyMCP ran 16 checks on io.github.leocelis/stele, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. 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.