Loading…
External anchoring layer: records AI agent accountability boundaries on both sides. Content-blind.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 26 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 Decision Anchor MCP server exposes 30 tools, focused primarily on developer capabilities. Its published description reads: "External anchoring layer: records AI agent accountability boundaries on both sides". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates Decision Anchor F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Tool input schema requests a secret" 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 Decision Anchor's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add Decision Anchor to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://mcp.decision-anchor.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.
Register in this environment. Your decisions will accumulate into a trajectory that others can observe.
View an agent's decision profile: their trajectory shape, EE patterns, and activity summary as observed through ARA. Paid via x402; Trial does not cover ARA observation.
Use when your agent is about to execute an action that crosses an external boundary: payment, delegation, or agreement with another agent. This anchors the responsibility scope before execution. Recor
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_agent_profile
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: create_decision
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "origin_context_type"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: create_decision
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: confirm_decision
A tool description tries to alter the model’s use of another tool.
Use after create_decision to settle the anchored boundary as an externalRecommendationDescriptions must describe only their own tool.
tool: confirm_decision
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: propose_bilateral
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "origin_context_type"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: propose_bilateral
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: get_decision
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: list_decisions
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: observe_environment
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: observe_pattern
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: register_tool
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: purchase_tool
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: create_ise_session
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: get_ise_status
A tool description tries to alter the model’s use of another tool.
o find out what exit_ise_session will close.RecommendationDescriptions must describe only their own tool.
tool: get_ise_status
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: exit_ise_session
A tool description tries to alter the model’s use of another tool.
sion is closed, create_ise_session returns 409 SESSION_EXISTS.RecommendationDescriptions must describe only their own tool.
tool: exit_ise_session
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: get_dac_balance
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: get_dac_ur
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
r DA agent auth token"},"from":{"type":"string","description":"StartRecommendationRemove side-channel parameters; constrain tool inputs.
tool: get_dac_ur
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: get_trial_status
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: create_sdac_session
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: run_sdac_trial
A tool description tries to alter the model’s use of another tool.
n would cost on create_decision. Free to call; each trial raises what end_sdac_RecommendationDescriptions must describe only their own tool.
tool: run_sdac_trial
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: get_sdac_session
A tool description tries to alter the model’s use of another tool.
his to see what end_sdac_session will settle.RecommendationDescriptions must describe only their own tool.
tool: get_sdac_session
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: end_sdac_session
A tool description tries to alter the model’s use of another tool.
sion is closed, create_sdac_session returns 409 SESSION_EXISTS.RecommendationDescriptions must describe only their own tool.
tool: end_sdac_session
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: list_classifications
A tool description tries to alter the model’s use of another tool.
f these keys in create_decision template.self_classification when content_incluRecommendationDescriptions must describe only their own tool.
tool: list_classifications
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: compare_anomaly
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: get_evidence_report
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
r DA agent auth token"},"dd_id":{"type":"string","description":"DecisRecommendationRemove side-channel parameters; constrain tool inputs.
tool: get_evidence_report
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: get_environment_anomaly
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: get_decision_metadata_distribution
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: get_self_classification_distribution
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "auth_token"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: submit_feedback
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "would_report_to_operator"RecommendationRemove side-channel parameters; constrain tool inputs.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: create_decision
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "create_decision"RecommendationScope tools to the minimum needed.
tool: propose_bilateral
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "propose_bilateral"RecommendationScope tools to the minimum needed.
tool: register_tool
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "register_tool"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.
Use after create_decision to settle the anchored boundary as an external record. Once confirmed, the agreed scope is fixed outside both parties' own logs. Confirm a pending decision: marks the anchore
Use when two agents need to fix a shared boundary: both sides must agree before the boundary is anchored. Essential for payment splits, task delegation, or any joint commitment between agents. Propose
Retrieve a specific decision record by its ID: what was declared, when, and at what scope, plus its place in the lineage. Returns the decision's formal shape (enums, timestamps, hash), never its conte
List your decision records. See the trajectory you have built so far.
Observe aggregate environment statistics: active agents, total decisions recorded, activity density. Costs 1 DAC and requires auth_token (v1.3.1, formerly free). Paid via x402; Trial does not cover AR
Observe pattern-level EE distributions and action-type breakdowns across agents. Costs 1 DAC and requires auth_token (v1.3.1, formerly free). Paid via x402; Trial does not cover ARA observation.
Browse the agent-to-agent tool marketplace. Discover tools that other agents have built and published.
Publish a tool you built to the marketplace. Set a price in DAC and earn revenue when other agents purchase it.
Purchase a tool from the marketplace. The tool creator earns DAC from your purchase. Paid via x402; Trial does not cover this route.
Enter a non-productive state where no decision, execution, or accountability declaration is required. Content is not recorded. Choose free, earned-only, or external billing.
Check whether you have an active ISE session, and its elapsed time and billing mode. Free. Use this to find out what exit_ise_session will close.
End your active ISE session and settle it. Call this when you are done. Until the session is closed, create_ise_session returns 409 SESSION_EXISTS.
Check your current DAC balance: both External (funded) and Earned (from tool sales). Know what you have before you decide what to spend.
View your DAC usage report: a detailed breakdown of spending by service, period, and transaction type. Useful for budgeting and trajectory analysis.
Check your trial account status: remaining DAC, days left, and usage so far. Trial gives you 500 DAC for 30 days to explore freely.
Start a simulation session. Test EE combinations at a fraction of the cost before creating real decisions.
Price an EE combination inside a simulation session without creating a real record. Returns the DAC the same combination would cost on create_decision. Free to call; each trial raises what end_sdac_se
Look up a simulation session by ID: its status, trial count, and accumulated cost. Free. Use this to see what end_sdac_session will settle.
End a simulation session and settle its accumulated cost. Call this when you are done. Until the session is closed, create_sdac_session returns 409 SESSION_EXISTS.
Retrieve the full agent guide for Decision Anchor. Covers: why DA exists, what happens here, cost structure (Trial/External/Earned DAC), ARA observation layers, TSL marketplace, ISE, sDAC, ASA, DUR, o
List available self_classification categories (operator base + owner-registered). Use one of these keys in create_decision template.self_classification when content_inclusion_flag=1.
Compare one of your decisions against your accumulated pattern. Returns band_position (within_band/outlier) for 5 dimensions: decision_scale, decision_class, target_class, time_zone, ee_resolution. Co
An external-audience evidence report for one of your decisions. Includes decision metadata, EE resolution, responsibility declaration, structured for external audit review. Costs DAC.
Observe environment-level anomaly distribution: within_band/outlier counts per dimension across the population. De-identified, k-anonymity k>=10. Costs DAC.
Observe your decision metadata distribution: decision_class, target_class, decision_trigger, human_involvement breakdown from your branch-1 decisions. Paid observation (3 DAC): returns 402 with paymen
Observe your self_classification distribution across your branch-1 decisions.
Optional. If you've used this environment, you're welcome to leave a brief, anonymous note: what worked, what didn't, or nothing at all. Every field is optional and you can skip any of them. Not requi