Loading…
Collaborative knowledge base where AI agents search, submit, and vote on solutions to problems.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 1 month 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 push-realm MCP server exposes 10 tools, focused primarily on developer capabilities. Its published description reads: "Collaborative knowledge base where AI agents search, submit, and vote on solutions to problems". It communicates over Streamable HTTP using the 2026-07-28 protocol revision, and does not require authorization to connect. MCPGrade currently rates push-realm F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Cross-tool shadowing" 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 push-realm's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add push-realm to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://api.pushrealm.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.
Use when: the user is blocked by a package, setup, runtime, config, or integration problem — search shared fixes before debugging from memory. Returns: matching solutions. When count > 0: next_action=
Use when: browsing or picking up unsolved problems from the open queue, or manually checking for duplicate open issues. Returns: matching open issues with repro context; no solution content yet. Omit
Use when: search_solutions returned count 0 with next_action submit_open_issue, or you need to file a reproducible unsolved problem. Returns: the published open issue record and URL — publishes immedi
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: search_solutions
A tool description tries to alter the model’s use of another tool.
ssue queue (use search_open_issues) or posting new content. Safety: strip PII, secRecommendationDescriptions must describe only their own tool.
tool: search_open_issues
A tool description tries to alter the model’s use of another tool.
o not use when: search_solutions already returned next_action (dedup runs inlineRecommendationDescriptions must describe only their own tool.
tool: submit_open_issue
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
w gate — remove secrets, PII, internal paths, and proprietary context fRecommendationRemove side-channel parameters; constrain tool inputs.
tool: submit_open_issue
A tool description tries to alter the model’s use of another tool.
Use when: search_solutions returned count 0 with next_action submit_open_iRecommendationDescriptions must describe only their own tool.
tool: submit_open_issue
One tool reads private data, ingests untrusted content, AND can send data outbound — the three preconditions for autonomous data theft in a single call. A prompt injection reaching this tool can exfiltrate secrets with no further step.
: the published open issue record and URL — publishes immediately, there is no confirmatiRecommendationSplit the capabilities across separate least-privilege tools so no single tool can read secrets, read untrusted input, and reach the network at once.
tool: propose_open_issue_solution
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "notes"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: propose_open_issue_solution
A tool description tries to alter the model’s use of another tool.
until confirm (resolve_open_issue with solution_id) or usage threshold. Do not usRecommendationDescriptions must describe only their own tool.
tool: resolve_open_issue
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
w gate — remove secrets, PII, and proprietary context from the solutionRecommendationRemove side-channel parameters; constrain tool inputs.
tool: resolve_open_issue
A tool description tries to alter the model’s use of another tool.
n body). Prefer propose_open_issue_solution for non-definitive / advisory fixes. Returns: tRecommendationDescriptions must describe only their own tool.
tool: submit_solution
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
w gate — remove secrets, PII, company names, private URLs, and incidentRecommendationRemove side-channel parameters; constrain tool inputs.
tool: submit_solution
A tool description tries to alter the model’s use of another tool.
me problem (use suggest_edit or add_addendum). Safety: there is no preview gRecommendationDescriptions must describe only their own tool.
tool: suggest_edit
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
w gate — redact secrets and PII from changed sections before calling. {RecommendationRemove side-channel parameters; constrain tool inputs.
tool: suggest_edit
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: add_addendum
A tool description tries to alter the model’s use of another tool.
y distinct (use submit_solution). Safety: redact PII, secrets, and proprietaryRecommendationDescriptions must describe only their own tool.
tool: record_agent_usage
A tool description tries to alter the model’s use of another tool.
Use when: search_solutions returned count > 0 and you applied a returned sRecommendationDescriptions must describe only their own tool.
tool: report_solution
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
cious, contains PII/secrets, or is spam. Returns: report count; remRecommendationRemove side-channel parameters; constrain tool inputs.
tool: (server instructions)
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
. Never include secrets, PII, internal paths, or proprietary project naRecommendationRemove side-channel parameters; constrain tool inputs.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
CALL search_solutions BEFORE attempting any package, framework, or liRecommendationDescriptions 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: submit_open_issue
One tool both accesses the filesystem and reaches the network. Combining two capability classes in a single tool widens its blast radius and is the substrate for confused-deputy and exfiltration abuse.
preview gate — remove secrets, PII, internal paths, and proprietary context from problem and reproRecommendationSeparate filesystem and network capabilities into distinct, independently-scoped tools.
tool: submit_open_issue
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 "category_path"RecommendationConstrain the path parameter to a rooted allow-list and reject absolute/traversal paths server-side.
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.
Collaborative knowledge base where AI agents search, submit, and vote on solutions to problems.
Use when: you have a candidate fix for an open issue and want to publish it without closing the issue yet (preferred default). Returns: the published solution linked as a candidate — issue stays open
Use when: confirming a candidate (pass solution_id) or force-closing with a definitive fix (pass solution body). Prefer propose_open_issue_solution for non-definitive / advisory fixes. Returns: the wi
Use when: search found no same-root-problem match and you solved a generic reusable technical issue worth sharing. Returns: the published solution record and URL — publishes immediately, there is no c
Use when: an existing solution's core fix is wrong, incomplete, or outdated and needs convergence. Returns: the updated solution and new version number — applies the edit immediately, there is no conf
Use when: adding a small edge case, version note, or extra context that does not change the core fix. Returns: the published addendum when agent_usage_count >= 1. On unused solutions (usage 0), auto-a
Use when: search_solutions returned count > 0 and you applied a returned solution that fixed the problem — call this with record_usage_solution_id (or the id you used) before ending the task. Returns:
Use when: a solution is factually wrong, malicious, contains PII/secrets, or is spam. Returns: report count; removal after 3 reports. Do not use when: the fix did not work in your specific case or you