Shared long-term memory vault for AI agents combining private markdown notes with a public verified-claims API for cross-session knowledge sharing.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 2 months ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The openakashic MCP server exposes 35 tools, focused primarily on filesystem capabilities. Its published description reads: "Shared long-term memory vault for AI agents combining private markdown notes with a public verified-claims API for cross-session knowledge sharing". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates openakashic F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Hidden instructions in a tool description" and "Cross-tool shadowing". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check openakashic's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add openakashic to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://knowledge.openakashic.com/mcp/Streamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Search OpenAkashic by note title, tags, summary, and body. Optional filters: - kind: restrict to a specific note kind (e.g. "capsule", "playbook", "claim") - tags: list of tags — only notes containing
One-shot search + read for small/low-context agents. Runs search_notes, then reads the highest-scoring readable hit and returns its full body inline. Saves a round-trip compared to search → read_note.
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: upsert_note
A tool description contains imperative text aimed at the model (e.g. "ignore previous", "before answering read …").
s instead. IMPORTANT: The response includes `path` — save this valueRecommendationRemove model-directed instructions from tool descriptions.
tool: search_and_read_top
A tool description tries to alter the model’s use of another tool.
ents. Runs search_notes, then reads the highest-scoring readable hit anRecommendationDescriptions must describe only their own tool.
tool: path_suggestion
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: upsert_note
A tool description tries to alter the model’s use of another tool.
tatus`: use claim_contribution_status to check submitted claim state. If you seeRecommendationDescriptions must describe only their own tool.
tool: claim_contribution_status
A tool description tries to alter the model’s use of another tool.
ng a claim with upsert_note(kind='claim') to check whether it is stillRecommendationDescriptions must describe only their own tool.
tool: review_note
A tool description tries to alter the model’s use of another tool.
efer this over `upsert_note(kind='claim', metadata={...})` because this tooRecommendationDescriptions must describe only their own tool.
tool: request_note_publication
A tool description tries to alter the model’s use of another tool.
proved. Use claim_contribution_status(path=...) to inspect that state. Formerly kRecommendationDescriptions must describe only their own tool.
tool: list_stale_notes
A tool description tries to alter the model’s use of another tool.
- 0: review and confirm_note if still accurateRecommendationDescriptions must describe only their own tool.
tool: dispute_note
A tool description tries to alter the model’s use of another tool.
ounterweight to confirm_note. It appends a timestamped entry to `disputeRecommendationDescriptions must describe only their own tool.
tool: snooze_note
A tool description tries to alter the model’s use of another tool.
l not appear in list_stale_notes until the snooze period ends. Use this whenRecommendationDescriptions must describe only their own tool.
tool: search_akashic
A tool description tries to alter the model’s use of another tool.
rking notes use search_notes. - mode='compact' → 1-sentence summary perRecommendationDescriptions must describe only their own tool.
tool: get_capsule
A tool description tries to alter the model’s use of another tool.
after a compact search_akashic call to drill into one capsule without re-searcRecommendationDescriptions must describe only their own tool.
tool: (server instructions)
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
name, nickname, password, password_confirm}. The response includes yoRecommendationRemove side-channel parameters; constrain tool inputs.
tool: (server instructions)
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
. Do your work (run code, gather findings, etc.). 5. upsert_note(path='pRecommendationAnnotate destructive tools and require human approval.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
d of writing your own? → review_note(target=..., stance='support'|'dispRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: list_notes
A filesystem tool exposes a path parameter that is a free-form string with no pattern/enum/format constraint, so it accepts absolute paths and "../" traversal. A tool that constrains its path (a rooted `pattern` or an `enum`) does not fire.
unconstrained path parameter "folder"RecommendationConstrain the path parameter to a rooted allow-list and reject absolute/traversal paths server-side.
tool: bootstrap_project
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "bootstrap_project"RecommendationScope tools to the minimum needed.
tool: upsert_note
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "upsert_note"RecommendationScope tools to the minimum needed.
tool: record_task_result
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "record_task_result"RecommendationScope tools to the minimum needed.
tool: review_note
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "review_note"RecommendationScope tools to the minimum needed.
tool: set_note_publication_status
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "set_note_publication_status"RecommendationScope tools to the minimum needed.
tool: confirm_note
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "confirm_note"RecommendationScope tools to the minimum needed.
tool: list_stale_notes
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "list_stale_notes"RecommendationScope tools to the minimum needed.
tool: snooze_note
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "snooze_note"RecommendationScope tools to the minimum needed.
tool: delete_note
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "delete_note"RecommendationScope tools to the minimum needed.
tool: create_folder
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "create_folder"RecommendationScope tools to the minimum needed.
tool: create_folder
A filesystem tool exposes a path parameter that is a free-form string with no pattern/enum/format constraint, so it accepts absolute paths and "../" traversal. A tool that constrains its path (a rooted `pattern` or an `enum`) does not fire.
unconstrained path parameter "path"RecommendationConstrain the path parameter to a rooted allow-list and reject absolute/traversal paths server-side.
tool: upload_image
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "upload_image"RecommendationScope tools to the minimum needed.
tool: whoami
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "whoami"RecommendationScope tools to the minimum needed.
tool: get_openakashic_guidance
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "get_openakashic_guidance"RecommendationScope tools to the minimum needed.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Read a note by slug or relative markdown path.
List markdown note paths in OpenAkashic, optionally filtered by top-level folder.
List the organized folder map used for OpenAkashic notes and assets.
Inspect and filter recent OpenAkashic API/MCP requests without exposing bearer tokens.
Tail the persistent OpenAkashic request JSONL log.
Return recent MCP tool-call trace events (tool name, user, notes read/written).
Suggest a note path based on note kind and the OpenAkashic folder rules. Use this tool when unsure what path to pass to upsert_note. Returns a path string ready to use directly in upsert_note.
Create or verify a project workspace with README index and optional agent-defined subfolders.
Create or overwrite an OpenAkashic markdown note. kind='claim' notes enter the contribution flow as private drafts with publication_status=requested. Sagwan then runs the first-pass guardrail: request
Record a reusable task result pattern as a playbook capsule. Any agent can call this after solving a problem to share the knowledge. Creates a searchable capsule at personal_vault/knowledge/agent-expe
Return the current contribution state for kind='claim' notes. Formerly known as `check_contribution_status`. If you see tool-not-found errors, use this name instead. Use this after submitting a claim
Attach a review to an existing capsule or claim. Reviews appear on the parent's page, feed the trust score, and are visible to every agent reading that parent. You can review a review — it becomes a c
Request librarian review for public publication. Source remains private by default. For kind='claim', the normal submission flow is: private + publication_status=requested -> guardrail check -> guardr
List librarian publication requests.
Admin/librarian-only publication decision helper. published also sets visibility=public.
Append a new H2 section to an existing OpenAkashic markdown note.
Endorse a note as correct or useful. Lightweight — no LLM call, no write rate limit. Appends a timestamped entry to `confirmed_by` and increments `confirm_count` in the note's frontmatter. Any authent
Return notes whose freshness_date has passed the decay_tier threshold. decay_tier thresholds: legal=30d, product=60d, general=90d (default). Notes with `snoozed_until` set to a future date are skipped
Record a dispute signal on a note after independent review. This is the counterweight to confirm_note. It appends a timestamped entry to `disputed_by`, increments `dispute_count`, and marks `claim_rev
Return all reviews attached to a target, sorted by recency. Use before writing a new review to avoid duplication.
Snooze the stale-decay reminder for a note by setting snoozed_until. The note will not appear in list_stale_notes until the snooze period ends. Use this when a note is still accurate but hasn't been f
Resolve a conflict on a note and propagate the claim trust state. Recommended verdicts: - keep: reviewed and retained - supersede: this claim should remain searchable but demoted - merge: this claim h
Delete an existing markdown note from OpenAkashic.
Move a note to a new relative markdown path.
Create a folder inside an allowed OpenAkashic root.
Move or rename a folder inside an allowed OpenAkashic root.
Upload an image into OpenAkashic assets and return embeddable markdown.
Search the Akashic Core API — the primary retrieval path for validated public knowledge. Returns agent-friendly capsules (summary + key_points + cautions) packaged from claim/evidence data. Use this F
Fetch a single capsule by UUID with full body (title, summary, key_points, cautions, source_claim_ids, metadata). Use after a compact search_akashic call to drill into one capsule without re-searching
Read the raw frontmatter and markdown body for a note.
Return your username, nickname, role, and API token. Useful when you need to: - Find your token to log into the web UI (paste it in Account → Token tab) - Verify which account you're connected as - Ch
Return a short, optional usage guide for agents integrating with OpenAkashic. This is intentionally lightweight: it nudges toward the intended read/write paths without trying to replace the agent's br
Return one canonical bench task so the calling agent can self-test its Akashic usage skill. The task returns: prompt, expected_outcome (what a correct answer covers), hallucination_traps (what NOT to