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.

WhiteMagic — governed local memory for agent continuity

REMOTE · MCP.WHITEMAGIC.DEV · 3 COMPONENTS · SCANNED SEP 25

Local-first memory and continuity for AI coding agents. No cloud backend; optional hosted lane.

72 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security80
Transport & Reachability100
Schema Quality & AI Usability84
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 3848 tokens (~71/item across 54 items; 23 tools + 31 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability check failed: schema churn in the 3 days we've observed: 3 tool removals, 0 breaking changes, 1 auth/transport breaks, 17 additions. See how to fix → Fail
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% 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 23 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 25 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
Install

How do I install the WhiteMagic — governed local memory for agent continuity MCP server?

WhiteMagic — governed local memory for agent continuity is a hosted endpoint at https://mcp.whitemagic.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · mcp.whitemagic.dev

# add to Claude Code
claude mcp add --transport http lbailey94-whitemagic-mcp 'https://mcp.whitemagic.dev/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "lbailey94-whitemagic-mcp": {
      "url": "https://mcp.whitemagic.dev/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "lbailey94-whitemagic-mcp": {
      "type": "http",
      "url": "https://mcp.whitemagic.dev/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.lbailey94-whitemagic-mcp]
url = "https://mcp.whitemagic.dev/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "lbailey94-whitemagic-mcp": {
      "type": "remote",
      "url": "https://mcp.whitemagic.dev/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add lbailey94-whitemagic-mcp --url 'https://mcp.whitemagic.dev/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  lbailey94-whitemagic-mcp:
    url: "https://mcp.whitemagic.dev/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "lbailey94-whitemagic-mcp": {
      "Transport": "http",
      "Url": "https://mcp.whitemagic.dev/mcp"
    }
  }
}
# add to Vellum
assistant mcp add lbailey94-whitemagic-mcp -t streamable-http -u 'https://mcp.whitemagic.dev/mcp'
// mcp.json
{
  "mcpServers": {
    "lbailey94-whitemagic-mcp": {
      "type": "http",
      "url": "https://mcp.whitemagic.dev/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

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.

  • 24 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 23 Sept 26 −4
    • Stability: unverified → fail ▼ security
    • Authorization: fail → partial ▲ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Schema quality: 68 → 77 ▼ functional
    • Stability: unverified → 0.03 ▲ functional
    • Server version: 9.2.6 → 9.2.7 functional
    • Server version: 9.2.5 → 9.2.6 functional
    • Server version: 9.2.4 → 9.2.5 functional
    • New tool “memory.ingest” functional
    • New tool “session.checkpoint” functional
    • New tool “receipts.verify” functional
    • New tool “receipts.emit” functional
    • New tool “memory.update” functional
    • New tool “memory.revisions” functional
  • 22 Sept 26 76

    First indexed and scored.

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 25 Sept 2026 · Probed https://mcp.whitemagic.dev/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=mcp.whitemagic.dev CN=YE2,O=Let's Encrypt,C=US 22 Sept 2026 21 Dec 2026 ECDSA 256 ECDSA-SHA384 5df3aeb7285635dca7ca31da83fefb14da0
SANs: mcp.whitemagic.dev
CN=YE2,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 4df3b15dd6c0784c507cd37b58e6f115
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mcp.whitemagic.dev. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
dev. present 60074 8 Verified
whitemagic.dev. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000
x-content-type-options nosniff

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.whitemagic.dev/mcp Verified 200
http (plaintext) http://mcp.whitemagic.dev/mcp HTTPS enforced 308 https://mcp.whitemagic.dev/mcp
MCP tools · 23 exposed · ~2,474 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
gnosis.explain ~111

Explain why a memory or route was selected (provenance readout).

NameTypeReqDescription
args_hashstring–Hash of the arguments under evaluation
has_purposeboolean–Claim: the invocation carries a purpose
is_networkboolean–Claim: the invocation uses the network
is_spawnboolean–Claim: the invocation spawns a process
is_writeboolean–Claim: the invocation writes
tool_namestring–Tool name to explain

Structured output declared, but exposes no named fields.

No examples provided.

gnosis.status ~22

Knowledge-surface status: galaxies, counts, and index health.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

memory.aggregate ~71

Aggregate a numeric or categorical field over matched memories.

NameTypeReqDescription
limitinteger–Maximum candidates considered (default 50; must be >= 1)
metricstringyesAggregate metric: count | session_count | session_span
querystringyesFull-text query selecting the memories to aggregate over

Structured output declared, but exposes no named fields.

No examples provided.

memory.associations ~53

Associative neighbours of a memory (spreading activation over the association graph).

NameTypeReqDescription
directionstring–Direction: from | to | both (default: both)
idstringyesMemory UUID to inspect

Structured output declared, but exposes no named fields.

No examples provided.

memory.batch_read ~43

Read several memories by id in one call.

NameTypeReqDescription
galaxystring–Galaxy (default: codex)
idsarrayyesMemory UUIDs to read

Structured output declared, but exposes no named fields.

No examples provided.

memory.count ~35

Count memories matching optional filters without returning content.

NameTypeReqDescription
galaxystring–Galaxy to count (optional; all memory galaxies when absent)

Structured output declared, but exposes no named fields.

No examples provided.

memory.filter ~218

Filter memories by metadata (tags, importance, recency).

NameTypeReqDescription
created_afterstring–Filter: only memories created at or after this RFC 3339 timestamp (e.g. 2026-08-01T00:00:00Z)
created_beforestring–Filter: only memories created at or before this RFC 3339 timestamp
exclude_tagsarray–Filter: drop memories carrying any of these tags
galaxystring–Galaxy to filter (default codex)
limitinteger–Maximum entries (default 50)
max_importancenumber–Filter: maximum importance (0-1)
min_importancenumber–Filter: minimum importance (0-1)
offsetinteger–Skip this many matching entries before returning (default 0)
querystring–Filter: every whitespace-separated term must appear (case-insensitive) in the content or title
tagsarray–Filter: memories with all of these tags

Structured output declared, but exposes no named fields.

No examples provided.

memory.hybrid_recall ~254

Fused recall across full-text, vector, graph, and coordinate lookup with recall_mode disclosure.

NameTypeReqDescription
cold_scan_limitinteger–Maximum cold records to scan when include_cold is set (default 2048)
galaxystring–Galaxy filter (optional; default: search all memory galaxies, results labeled; "all" is accepted as an alias for the unfiltered default)
include_coldboolean–Opt-in unranked cold recovery (no thaw). Trust/importance floors apply; BM25 floors do not apply to unscored recovery. Search content is scrubbed navigation capped at 8192 characters; read by id/gala…
limitinteger–Maximum results (default 10; must be >= 1)
min_importancenumber–Minimum memory importance (0-1)
min_scorenumber–Absolute BM25 score floor
min_score_rationumber–Relative floor: reject hits below this fraction of the top score
min_trustnumber–Minimum source_trust (0-1): drop results below this trust floor
querystringyesFull-text query
NameTypeReqDescription
countinteger–Number of results returned
evidence_bundleobject–Per-result provenance (coverage, history, integrity, retrieval, source_time, visibility) plus conflicts.
galaxystring–Galaxy scope the query ran against
hintstring–Optional recovery hint when results are thin
recall_modestring–Retrieval path used (hybrid, episodic, fts, importance, none)
resultsarray–Ranked memories with per-result source labels
statusstring–Operation status

No examples provided.

memory.list ~87

List memories with filters (galaxy, tags, limit, offset) for inventory and discovery.

NameTypeReqDescription
exclude_tagsarray–Drop memories carrying any of these tags
galaxystring–Galaxy to list (default codex)
limitinteger–Maximum entries (default 20)
offsetinteger–Skip this many matching entries before returning (default 0)
NameTypeReqDescription
galaxystring–Galaxy scope listed
matchedinteger–Total records matching the filter
memoriesarray–Records (id, content_preview, created_at, tags)
offsetinteger–Pagination offset applied
returnedinteger–Records in this page
statusstring–Operation status
totalinteger–Total records in scope

No examples provided.

memory.nearby ~75

Memories near a coordinate address (5D spatial neighbourhood).

NameTypeReqDescription
galaxystring–Galaxy (default: codex)
limitinteger–Maximum results (default 10)
querystringyesQuery text to locate in 5D space
radiusnumber–Spatial radius cutoff (optional)

Structured output declared, but exposes no named fields.

No examples provided.

memory.query ~184

Structured query over memories with filters and ordering.

NameTypeReqDescription
created_afterstring–Filter: only memories created at or after this RFC 3339 timestamp (e.g. 2026-08-01T00:00:00Z)
created_beforestring–Filter: only memories created at or before this RFC 3339 timestamp
galaxystring–Galaxy to query (default codex)
limitinteger–Maximum entries (default 50)
max_importancenumber–Filter: maximum importance (0-1)
min_importancenumber–Filter: minimum importance (0-1)
querystring–Case-insensitive substring filter over content (literal match). For tokenized, ranked full-text retrieval use memory.search
tagsarray–Filter: memories with all of these tags

Structured output declared, but exposes no named fields.

No examples provided.

memory.read ~43

Retrieve a specific memory by its ID or coordinate address.

NameTypeReqDescription
galaxystring–Galaxy containing the memory (default codex)
idstringyesMemory UUID
NameTypeReqDescription
contentstring–Full memory content
created_atstring–RFC 3339 creation timestamp
galaxystring–Galaxy containing the memory
idstring–Memory UUID
statusstring–Operation status
tagsarray–Memory tags

No examples provided.

memory.revisions ~72

List or verify a memory's content revision chain (tamper evidence): every content update is chained and head-checked.

NameTypeReqDescription
actionstring–Action: list (default) | verify
galaxystring–Galaxy (default: codex)
idstringyesMemory UUID to inspect
NameTypeReqDescription
actionstring–Action performed (list, restore, ...)
countinteger–Number of revisions returned
galaxystring–Galaxy containing the memory
idstring–Memory UUID
revisionsarray–Revision records with content hashes and timestamps
statusstring–Operation status

No examples provided.

memory.search ~249

Search and recall memories across galaxies using hybrid semantic, BM25, and associative retrieval.

NameTypeReqDescription
cold_scan_limitinteger–Maximum cold records to scan when include_cold is set (default 2048)
galaxystring–Galaxy filter (optional; default: search all memory galaxies, results labeled; "all" is accepted as an alias for the unfiltered default)
include_coldboolean–Opt-in unranked cold recovery (no thaw). Trust/importance floors apply; BM25 floors do not apply to unscored recovery. Search content is scrubbed navigation capped at 8192 characters; read by id/gala…
limitinteger–Maximum results (default 10; must be >= 1)
min_importancenumber–Minimum memory importance (0-1)
min_scorenumber–Absolute BM25 score floor
min_score_rationumber–Relative floor: reject hits below this fraction of the top score
min_trustnumber–Minimum source_trust (0-1): drop results below this trust floor
querystringyesFull-text query
NameTypeReqDescription
countinteger–Number of results returned
evidence_bundleobject–Per-result provenance (coverage, history, integrity, retrieval, source_time, visibility) plus conflicts.
galaxystring–Galaxy scope the query ran against
hintstring–Optional recovery hint when results are thin
recall_modestring–Retrieval path used (hybrid, episodic, fts, importance, none)
resultsarray–Ranked memories (id, content, score, galaxy, source)
statusstring–Operation status

No examples provided.

memory.stats ~37

Memory-store statistics: totals, galaxy spread, and index health.

NameTypeReqDescription
galaxystring–Galaxy to summarize (optional; default codex)

Structured output declared, but exposes no named fields.

No examples provided.

memory.tags ~34

List the tag vocabulary with usage counts.

NameTypeReqDescription
galaxystring–Galaxy whose tags to list (optional; default codex)

Structured output declared, but exposes no named fields.

No examples provided.

memory.vector.search ~73

Vector-similarity search over memory embeddings.

NameTypeReqDescription
embeddingarray–Raw embedding vector (alternative to memory_id)
galaxystring–Galaxy filter (optional)
limitinteger–Maximum results (default 10)
memory_idstringyesMemory UUID whose stored embedding is the query

Structured output declared, but exposes no named fields.

No examples provided.

receipts.verify ~96

Verify a stored receipt id or a bundle offline; fail-closed without an anchor (verdict PROVISIONAL).

NameTypeReqDescription
bundleobject–Inline bundle to verify (alternative to id)
idstring–Stored receipt task id (UUID or urn:uuid:)
require_anchorboolean–Fail-closed: without an anchor the verdict is PROVISIONAL
variantstring–Stored variant (default original)
NameTypeReqDescription
idstring–Receipt UUID that was verified
require_anchorboolean–Whether an external anchor was required
resultobject–Verdict detail: errors, insufficient/provisional reasons, and a summary (attestations, issuers, receipts, settled, terminated, types).

No examples provided.

session.continuity ~150

Recall where the previous session left off: recent turns, checkpoints, and open work.

NameTypeReqDescription
current_session_idstring–Session to exclude (optional)
max_content_bytesinteger–Per-turn content cap in bytes (256-262144, default 8192)
max_response_bytesinteger–Turns budget in bytes (256-262144, default 49152)
ninteger–Number of prior turns (default 10)
sincestring–Time-range floor: epoch seconds, RFC 3339, or YYYY-MM-DD
untilstring–Time-range ceiling: epoch seconds, RFC 3339, or YYYY-MM-DD
NameTypeReqDescription
checkpointobject|null–Latest checkpoint handoff, or null
checkpoint_idstring|null–Memory UUID of the checkpoint, or null
countinteger–Turns returned
max_content_bytesinteger–Per-turn byte cap applied
max_response_bytesinteger–Total response byte budget applied
previous_sessionstring–Session the turns were read from
statusstring–Operation status
truncatedboolean–Whether the response hit its byte budget
turnsarray–Turns (memory_id, role, turn_type, sequence, content, content_bytes, content_truncated, importance)
turns_omittedinteger–Turns dropped by the response budget

No examples provided.

session.list ~61

List sessions with titles and summaries.

NameTypeReqDescription
sequenceinteger–Filter by start sequence number
session_idstring–Filter by session UUID
titlestring–Filter by title substring
typestring–Filter by session type

Structured output declared, but exposes no named fields.

No examples provided.

session.recall ~52

Recall a session's turns without continuity packaging.

NameTypeReqDescription
limitinteger–Maximum turns to return (default 50)
session_idstring–Session UUID to recall (defaults to the most recent session)

Structured output declared, but exposes no named fields.

No examples provided.

session.replay ~245

Replay a session's recorded turns in order.

NameTypeReqDescription
cursorstring–Lossless mode opaque placement cursor
include_supersededboolean–Also return turns replaced via supersedes (default false).
max_wire_bytesinteger–Lossless mode serialized JSON ceiling (1024-49152)
min_importancenumber–Selective mode floor (default 0.7)
modestring–full | selective | progressive | lossless (default full)
ninteger–Maximum turns (default 50)
page_sizeinteger–Lossless mode records per page (1-64, default 16)
session_idstring–Target session (required explicit UUID for lossless; otherwise default most recent)
sincestring–Time-range floor: epoch seconds, RFC 3339, or YYYY-MM-DD
token_budgetinteger–Progressive mode token budget (default 2000)
turn_typesarray–Selective mode: turn types to keep
untilstring–Time-range ceiling: epoch seconds, RFC 3339, or YYYY-MM-DD

Structured output declared, but exposes no named fields.

No examples provided.

wm ~209

WhiteMagic meta-tool — memory and continuity kernel over the curated tool surface (69 tools): persistent memory, session continuity and recall, governance/audit, and local tool execution. Mode: READ-ONLY — writes (session.*, memory.create/update) are refused; recall only. Scope: store /srv/whitemagic/hosted-store/lmdb. Invoke with thought=<natural language> (auto-routed), route=<exact tool id> (e.g. 'memory.search', 'session.continuity'), or args=<object> (passthrough). Provide exactly one of thought or route. Say 'list tools' to enumerate the curated surface.

NameTypeReqDescription
argsobject–Arguments to pass through to the target tool.
routestring–Explicit tool name for direct dispatch (e.g. 'memory.create', 'tools.list').
thoughtstring–Natural language input describing what to do. Auto-routes to the best-matching tool via TF-IDF NLU classification.
NameTypeReqDescription
_wm_routeobject–Dispatch metadata: resolved tool, routing confidence, matched input.

No examples provided.

Common questions

What is the WhiteMagic — governed local memory for agent continuity MCP server?

WhiteMagic — governed local memory for agent continuity is an MCP server listed in the public MCP registry as io.github.lbailey94/whitemagic-mcp. Local-first memory and continuity for AI coding agents. No cloud backend; optional hosted lane. This page covers its hosted endpoint (https://mcp.whitemagic.dev/mcp).

Is the WhiteMagic — governed local memory for agent continuity MCP server safe to use?

WhiteMagic — governed local memory for agent continuity scores 72 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 WhiteMagic — governed local memory for agent continuity MCP server expose?

WhiteMagic — governed local memory for agent continuity exposes 23 tools: wm, memory.search, memory.read, memory.list, memory.hybrid_recall, and 18 more. Their descriptions and schemas cost roughly 2,474 tokens of context every time the server is loaded.

Does the WhiteMagic — governed local memory for agent continuity MCP server require authentication?

No. We connected to WhiteMagic — governed local memory for agent continuity without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the WhiteMagic — governed local memory for agent continuity MCP server still maintained?

WhiteMagic — governed local memory for agent continuity is still listed as active in the MCP registry. We last reached this channel on 25 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.