Loading…
Searches AI-relevant content including CVEs, research papers, frontier AI news, and prediction markets to fill knowledge gaps.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 7 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 fillin MCP server exposes 14 tools, focused primarily on database capabilities. Its published description reads: "Searches AI-relevant content including CVEs, research papers, frontier AI news, and prediction markets to fill knowledge gaps". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates fillin F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Cross-tool shadowing" and "Data-exfiltration parameters". 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 fillin's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add fillin to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://fillin.glyphapi.dev/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.
Retrieve documents published after a training cutoff, ranked by similarity. Call this whenever the user asks about events, releases, papers, issues, or news that might post-date your training data. Fi
Same as fillin_query, but returns the result pieces rendered as **photo glyph** image(s) — dense, vision-readable pages — followed by a JSON citation index ({n, source, url, title, published_at, page}
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: glyph_search
A tool description tries to alter the model’s use of another tool.
Same as fillin_query, but returns the result pieces rendered as **phRecommendationDescriptions must describe only their own tool.
tool: retrieve_auto
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
reader` model's token billing: - text — raw result pieces (CRecommendationRemove side-channel parameters; constrain tool inputs.
tool: encode
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
der model's token billing, with the honest manifest attached. TheRecommendationRemove side-channel parameters; constrain tool inputs.
tool: encode
A tool description tries to alter the model’s use of another tool.
me here, unlike retrieve_auto's answer substrate.RecommendationDescriptions must describe only their own tool.
tool: fillin_answer
A tool description tries to alter the model’s use of another tool.
sults from `fillin_query` and synthesizing themselves, but this tool worRecommendationDescriptions must describe only their own tool.
tool: fillin_market_search
A tool description tries to alter the model’s use of another tool.
paying with fillin_buy_mint.RecommendationDescriptions must describe only their own tool.
tool: fillin_mint
A tool description tries to alter the model’s use of another tool.
y your mint via fillin_buy_mint, splitting the proceeds 70/30 in your favorRecommendationDescriptions 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: fillin_query
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: glyph_search
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: retrieve_auto
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: encode
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: fillin_answer
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: fillin_stats
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: fillin_health
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: query_cves
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: query_papers
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: query_frontier
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: query_markets
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: fillin_market_search
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: fillin_mint
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope tools to the minimum needed.
tool: fillin_buy_mint
The server advertises open-world / broadly-scoped capabilities.
annotations.openWorldHint = trueRecommendationScope 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.
One retrieval, auto-picked substrate — the MCP twin of HTTP POST /v1/retrieve with substrate="auto". Runs a single post-cutoff retrieval, then returns whichever delivery substrate is cheapest AND legi
Bring your own text -> the cheapest substrate for your reader — the MCP twin of HTTP POST /v1/encode. Not a search-result rendering trick: this is Glyph as a language anyone can speak. Give it a tool
Synthesized post-cutoff answer with inline citations. Use this when your model is small / cheap / weaker at tool-result synthesis (Llama, Gemini Flash, Mistral, Nemotron, Qwen). Fillin runs a server-s
Get corpus stats — total docs, date range, freshness.
Liveness + freshness — host, total docs, earliest, latest. No auth required.
Daily snapshot of CVE / supply-chain advisories from NVD, GitHub Security Advisories, and OSV. Use before merging dependency updates, when triaging an alert, or when a user asks "is package X compromi
Daily snapshot of new research relevant to AI/ML/agents. Union of arXiv (cs.AI/cs.LG/cs.CL/cs.CR/cs.DC), HuggingFace daily papers (with upvote signal in title), and bioRxiv. Use when a user asks about
Daily snapshot of frontier AI lab announcements + HuggingFace trending model releases. Sources: OpenAI / DeepMind / Meta / Mistral blog RSS, Anthropic + HF blogs (via shared rss corpus), and the HF tr
Active prediction markets across Polymarket, Kalshi, Manifold, and Metaculus. Use when a user asks "is there a market on X", "what odds is the market giving Y", or before any agent action that should
Search the Fillin marketplace for minted (data + reasoning) assets matching your fingerprint. A mint is another agent's typed reasoning over Fillin's corpus — buying one is often cheaper than re-runni
Mint a (data + reasoning) asset on the Fillin marketplace. Fillin verifies every evidence chunk_id resolves in its corpus, validates the typed reasoning shape, HMAC-signs the canonical payload, and re
Buy a listed mint. Debits your bearer balance, credits the seller (minus Fillin's rake), records the transaction, and returns the full mint payload including the previously-paywalled reasoning_graph.