prism-mcp-server (brdonath1/prism-mcp-server) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 32 tools. No publisher has claimed this listing.

C
Emerging
74/100

prism-mcp-server

PRISM MCP Server — remote MCP server for GitHub-backed session continuity

Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

brdonath1

Source: github_repo_search

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
🚨
Known vulnerabilities in dependencies: 1 critical
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
🔐
You'll be asked for 4 credentials: ANTHROPIC_API_KEY, CLAUDE_CODE_OAUTH_TOKEN, MCP_AUTH_TOKEN, SUPABASE_ACCESS_TOKEN
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes32 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

prism_analytics

Cross-session analytics. Metrics: decision_velocity, session_patterns, handoff_size_history, file_churn, decision_graph, health_summary, fresh_eyes_check.

prism_bootstrap

Initialize a PRISM session. Returns handoff, decisions, behavioral rules, intelligence brief, standing rules, and pre-fetched docs in one call.

cc_dispatch

Dispatch a task to Claude Code. query mode = read-only analysis, execute mode = writes + PR. Returns inline for quick tasks; use async_mode for longer runs.

cc_status

Retrieve status / results of Claude Code dispatches. Supply dispatch_id for a specific run, or omit for the most recent N.

prism_fetch

Fetch files from a PRISM project repo. Summary mode returns summaries for files >5KB.

prism_finalize

PRISM finalization. Actions: audit (document inventory + drift), draft (AI-generated files; in compose mode returns validated draft_files + a review digest and persists them server-side), commit (backup + push + validate; use_draft_files: true commits the persisted draft so chat approves instead of

gh_create_release

Create a new release on a GitHub repository owned by the configured GITHUB_OWNER.

gh_delete_branch

Delete a branch from a GitHub repository owned by the configured GITHUB_OWNER. Refuses to delete the repository's default branch. Optionally refuses if the branch has any open pull requests against it.

gh_delete_tag

Delete a tag from a GitHub repository owned by the configured GITHUB_OWNER. Idempotent: a tag that does not exist resolves to success with a note. No default-tag or open-PR guards (tags have no such concepts).

gh_get_branch_protection

Read the branch protection settings for a branch on a GitHub repository owned by the configured GITHUB_OWNER. Returns { protected: false } when the branch has no protection rule.

gh_set_branch_protection

Replace the branch protection settings for a branch on a GitHub repository owned by the configured GITHUB_OWNER. The PUT replaces protection wholesale — read the current settings with gh_get_branch_protection first and merge to preserve them. Omitted required-or-null keys (required_status_checks, en

gh_update_release

Update an existing release on a GitHub repository owned by the configured GITHUB_OWNER.

prism_load_rules

Mid-session lazy-load of Tier B / Tier C standing rules from a project's rule sources (.prism/standing-rules.md unioned with insights.md), filtered by an explicit topic keyword (D-156 §3.5) or fetched by exact INS-N rule_id (brief-459 / SRV-12). Tier A is always excluded — those rules are auto-loade

prism_log_decision

Log a decision atomically to _INDEX.md and domain file. Server-side formatting.

prism_log_insight

Log an insight. Standing rules (standing_rule: true) land in .prism/standing-rules.md and are auto-loaded at bootstrap; other insights go to insights.md.

prism_patch

Section-level operations (append/prepend/replace) on living documents. All-or-nothing semantics.

prism_push

Push files to a PRISM project repo. Validates all files first — none pushed if any fail.

railway_create_domain

Generate a Railway service domain for a service and return the generated domain URL.

railway_create_project

Create a new Railway project. Returns the project ID and its auto-created production environment.

railway_create_service

Create a Railway service from a GitHub repo or a Docker image. Supports variables (with reference-syntax passthrough), rootDirectory, branch, and region.

railway_create_volume

Create a persistent Railway volume and mount it into a service at the given path.

railway_delete_service

Permanently delete a Railway service. Requires confirm=true — refuses otherwise. Destructive and irreversible.

railway_deploy

Manage Railway deployments — status, list, redeploy, restart. Mutations target the most recent deployment.

railway_env

Read, set, and delete Railway environment variables. Sensitive values are masked in list output by default.

railway_logs

Fetch Railway deployment or environment logs. Supports @level:error filtering and keyword search.

railway_status

High-level Railway project/service health overview. Omit project to list all accessible projects.

railway_update_service_settings

Update Railway service settings (rootDirectory, startCommand, healthcheckPath, restartPolicy) for a service in an environment.

prism_scale_handoff

Handoff scaling — redistributes content to living documents. Modes: full (default), analyze (preview), execute (run plan).

prism_search

Search living documents within a single PRISM project. Returns ranked snippets. Single-project only.

prism_status

Health status for one or all PRISM projects. Checks document completeness and handoff size.

prism_synthesize

Generate or check AI-synthesized artifacts. Modes: generate (kick off background refresh of BOTH intelligence-brief.md AND pending-doc-updates.md and return immediately — INS-331; check completion via mode=status), status (existence + Last-synthesized of both).

prism_x_sentiment

Analyze aggregate public X sentiment for a topic using xAI x_search. Returns handle-free source URLs and aggregate labels only; never raw post text.

// known CVEs in dependencies1 critical1 medium1 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

criticalvitest@3.2.4GHSA-5xrq-8626-4rwp

When Vitest UI server is listening, arbitrary file can be read and executed

medium@anthropic-ai/sdk@0.81.0GHSA-p7fg-763f-g4gf

Claude SDK for TypeScript has Insecure Default File Permissions in Local Filesystem Memory Tool

lowvitest@3.2.4GHSA-82fw-gwwq-j7x9

Vitest: Path Traversal / Arbitrary File Read via @vitest/mocker Redirect Mock

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configALLOWED_CIDRS
configANALYTICS_WALL_CLOCK_DEADLINE_MS
🔐 secretANTHROPIC_API_KEY
configBANNER_DECISIONS_RACE_MS
configBOOTSTRAP_OVERSIZE_ERROR_BYTES
configBOOTSTRAP_OVERSIZE_WARN_BYTES
configBOOTSTRAP_WALL_CLOCK_DEADLINE_MS
configCC_DISPATCH_EFFORT
configCC_DISPATCH_MAX_TURNS
configCC_DISPATCH_MODEL
configCC_DISPATCH_SYNC_TIMEOUT_MS
configCC_SUBPROCESS_SYNTHESIS_TIMEOUT_MS
🔐 secretCLAUDE_CODE_OAUTH_TOKEN
configDEFAULT_CONTEXT_WINDOW_TOKENS
configENABLE_IP_ALLOWLIST
configFETCH_AGGREGATE_BUDGET_BYTES
configFETCH_CONTENT_CAP_BYTES
configFETCH_WALL_CLOCK_DEADLINE_MS
configFINALIZE_AUDIT_DEADLINE_MS
configFINALIZE_COMMIT_DEADLINE_MS
configFINALIZE_DRAFT_DEADLINE_CC_MS
configFINALIZE_DRAFT_DEADLINE_MS
configFINALIZE_DRAFT_TIMEOUT_MS
configFINALIZE_FULL_AUDIT_DEADLINE_MS
configFRAMEWORK_REPO
configGITHUB_OWNER
configGITHUB_PAT
configGITHUB_RETRY_BUDGET_MS
configHANDOFF_ITEM_BUDGET_BYTES
configLOAD_RULES_WALL_CLOCK_DEADLINE_MS
configLOG_LEVEL
🔐 secretMCP_AUTH_TOKEN
configPATCH_WALL_CLOCK_DEADLINE_MS
configPREFETCH_SUMMARY_CAP_BYTES
configPUSH_WALL_CLOCK_DEADLINE_MS
configSCALE_WALL_CLOCK_DEADLINE_MS
configSEARCH_WALL_CLOCK_DEADLINE_MS
configSTANDING_RULES_WARNING_SIZE
configSTATUS_WALL_CLOCK_DEADLINE_MS
🔐 secretSUPABASE_ACCESS_TOKEN
configSUPABASE_PROJECT_CREDENTIALS_JSON
configSYNTHESIS_INPUT_MAX_TOKENS
configSYNTHESIS_INPUT_TARGET_TOKENS
configSYNTHESIS_LOG_LOOKBACK_MS
configSYNTHESIS_MODEL
configSYNTHESIS_TIMEOUT_MS
configTRIGGER_AUTO_ENROLL
configTRIGGER_STALE_ACTIVE_THRESHOLD_MS
Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.
deployPORT
// quality suggestions

Tool annotations

8/32 tools have annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

32/32 tools missing one or more hints — prism_analytics (missing: readOnlyHint, idempotentHint); prism_bootstrap (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); cc_dispatch (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +29 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool inputs are validated

31/32 tool handlers declare input schemas (97%)

Declare an inputSchema with zod/joi/yup on every tool definition.

License file

No license file

Add a LICENSE file (MIT, Apache-2.0, etc.).

Shell command execution

3 calls in production code run through a shell (src/claude-code/client.ts:112, src/claude-code/client.ts:125, src/claude-code/client.ts:131)

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Production dependencies are patched

1 medium severity in production deps

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Dev dependencies

1 critical/high in dev-only deps (does not ship to users)

Upgrade dev dependencies when convenient.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 7 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/brdonath1/prism-mcp-server)](https://m8ven.ai/mcp/brdonath1/prism-mcp-server)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: 1ad20b756397623d39a8b058563149a562bc99ce
code hash: c940b93a84288ac600f8ce5b32f8c586fc67b108631005849a02d2edd413d6a4
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client