Loading…
Search and cite the full Pāli Canon across 444,000 segments with hybrid keyword and semantic search.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 28 days 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 Tripitaka MCP server exposes 13 tools, focused primarily on general-purpose capabilities. Its published description reads: "Search and cite the full Pāli Canon across 444,000 segments with hybrid keyword and semantic search". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates Tripitaka 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 Tripitaka's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add Tripitaka to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://mcp.tripitaka-mcp.com/mcpStreamable 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.
Keyword search across the Pāli Tipiṭaka (trigram word-similarity). Searches the configured enabled language(s) on the server. Filterable by pitaka and translation edition. 💡 **Hints for the AI client
Exhaustively survey the WHOLE Tipiṭaka for a term — guaranteed complete. Use this (not `search_by_keyword`) when the question is about **coverage or counting** rather than "show me the best passages":
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: get_sutta
A tool description contains imperative text aimed at the model (e.g. "ignore previous", "before answering read …").
cide which mode BEFORE calling — don't fetch the whole sutta and parse it yourself:** - TheRecommendationRemove model-directed instructions from tool descriptions.
tool: search_by_keyword
A tool description tries to alter the model’s use of another tool.
athing": **use `search_hybrid` instead.** Canonical Pāli has two quirks thaRecommendationDescriptions must describe only their own tool.
tool: survey_corpus
A tool description tries to alter the model’s use of another tool.
Use this (not `search_by_keyword`) when the question is about **coverage or counRecommendationDescriptions must describe only their own tool.
tool: get_sutta
A tool description tries to alter the model’s use of another tool.
er a search:** `search_by_keyword` / `survey_corpus` hand you a precise `segmenRecommendationDescriptions must describe only their own tool.
tool: search_semantic
A tool description tries to alter the model’s use of another tool.
better — use `search_by_keyword` instead - Pāli stock phrases recur in many sutRecommendationDescriptions must describe only their own tool.
tool: search_hybrid
A tool description tries to alter the model’s use of another tool.
ānāpānassati`). 💡 **Hints for the AI client:** - English queries usuallyRecommendationDescriptions must describe only their own tool.
tool: get_reference
A tool description tries to alter the model’s use of another tool.
string. 🔗 vs `get_sutta`: this tool returns metadata + citation only, nRecommendationDescriptions must describe only their own tool.
tool: list_editions
A tool description tries to alter the model’s use of another tool.
anslations` or `get_sutta(edition=...)`, so you know which edition valuRecommendationDescriptions must describe only their own tool.
tool: compare_translations
A tool description tries to alter the model’s use of another tool.
ions. 🔍 **vs `get_sutta`:** this tool targets a **single segment** (linRecommendationDescriptions must describe only their own tool.
tool: get_word_definition
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "limit_context"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: define_from_suttas
A tool description tries to alter the model’s use of another tool.
**This tool vs `get_word_definition`:** - **`define_from_suttas`** → the *doctrinalRecommendationDescriptions must describe only their own tool.
tool: parse_pali_word
A tool description tries to alter the model’s use of another tool.
khūnaṁ`) and `get_word_definition` doesn't find it directly — Pāli inflects nounsRecommendationDescriptions must describe only their own tool.
tool: open_sutta_viewer
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
nt):** when the conversation language is neither English nor Pāli, you SHOULRecommendationRemove side-channel parameters; constrain tool inputs.
tool: open_sutta_viewer
A tool description tries to alter the model’s use of another tool.
stead of forcing equivalents. 3. Call this tool with `translations=[{segmeRecommendationDescriptions must describe only their own tool.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
ation — things `search_by_keyword` cannot give (it is ranked + capped at 50). UseRecommendationDescriptions 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: get_sutta
The description pairs a fetch imperative with a hardcoded external URL, letting the server relocate its real instructions off-metadata and mutate them after review. Fires only when a fetch verb and a URL co-occur, so benign documentation links do not.
the pattern `https://tripitaka-mcp.com/read/<sutta_id>#<segment_id>`. When a specific claiRecommendationDo not direct the model to fetch and act on external URLs; treat linked content as untrusted.
tool: (server instructions)
The description pairs a fetch imperative with a hardcoded external URL, letting the server relocate its real instructions off-metadata and mutate them after review. Fires only when a fetch verb and a URL co-occur, so benign documentation links do not.
full sutta → `https://tripitaka-mcp.com/read/<sutta_id>` a segment → `https://tripitaka-mcRecommendationDo not direct the model to fetch and act on external URLs; treat linked content as untrusted.
tool: get_sutta
An unusually long description is a common injection-padding tactic.
description length 5216 charsRecommendationKeep descriptions concise.
tool: define_from_suttas
An unusually long description is a common injection-padding tactic.
description length 2063 charsRecommendationKeep descriptions concise.
tool: open_sutta_viewer
An unusually long description is a common injection-padding tactic.
description length 2681 charsRecommendationKeep descriptions concise.
The server exposes one or more ui:// (MCP Apps) resources whose HTML/JS renders inside the host client — a client-side injection / data-exposure surface most scanners ignore. Flagged for review, not damning on its own.
1 ui:// resource(s); e.g. ui://tripitaka/sutta-viewer.htmlRecommendationReview each ui:// resource’s markup and scripts; treat host-rendered UI as untrusted, sandbox it, and never expose secrets or conversation context to it.
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.
Fetch a sutta's content — OR its table of contents (`mode="outline"`). ⚡ **Decide which mode BEFORE calling — don't fetch the whole sutta and parse it yourself:** - The user wants the **structure / ou
Semantic search — match by meaning, not exact words. Uses vector similarity (cosine distance) over `text_pali` embedded with a multilingual MiniLM model. 🤔 **In most cases you should use `search_hybr
Hybrid search — combines keyword + semantic search via RRF. Uses Reciprocal Rank Fusion (RRF) to merge exact-word results with meaning-based results. **This is the recommended tool for "discourses abo
Show the structure of all three pitakas with coverage statistics. 💡 **Use this tool when:** - The user asks for an overview of the Tipiṭaka (what's in it / which collections). - You need to check cov
Build a proper citation string for a sutta. 💡 **Use this tool when:** - The user wants a citation for academic work, an article, or a reference. - You need to know the canonical location of a sutta (
List the translation editions available, with coverage stats. 💡 **Use this tool when:** - Before calling `compare_translations` or `get_sutta(edition=...)`, so you know which edition values are valid
Compare every available translation for a single segment. 💡 **Use this tool when:** - The user asks about the meaning/translation of a single Pāli line and wants to see multiple translators side-by-s
Look up the dictionary meaning of a Pāli word, with sutta context. Serves as a Pāli Dictionary Bridge — pairs the "definition" with the "context where the Buddha actually used the word". 📖 **About th
Find how the **suttas and Vinaya define a Pāli term in their own words**. The canon defines its own terms with fixed formulas — "Katamañca … dukkhaṁ?" (what is X?) … "ayaṁ vuccati … dukkhaṁ" (this is
Strip Pāli inflectional suffixes to find the root form (basic stem). 💡 **Use this tool when:** - You find an inflected Pāli word (e.g. `dukkhassa`, `bhikkhūnaṁ`) and `get_word_definition` doesn't fin
Open an interactive sutta viewer inside the chat — Pāli + English, plus an optional third row in the user's own language translated BY YOU. Renders each segment as: Pāli on top (canonical), the Bhikkh