Agent skill

Manage MCP Access

by speakeasy-api in speakeasy-api/gram

Create or select a narrow custom AICP MCP access role, assign it to an explicitly selected member, and verify local desired state while separating unverified provider synchronization.

AGPL-3.0Auto-check passedAgent Workflows

Install Manage MCP Access

skills CLI
$ npx skills add speakeasy-api/gram --skill manage-mcp-access -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install speakeasy-api/gram manage-mcp-access --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/speakeasy-api/gram.git skills-src && mkdir -p .claude/skills && cp -r skills-src/server/internal/plugins/platform_mcp_skills/manage-mcp-access .claude/skills/manage-mcp-access && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
manage-mcp-access
GitHub stars
273
Token cost
~2.4k tokens
SKILL.md length
1,358 words
Files
1
Skills in repo
39
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Create or select a narrow custom AICP MCP access role, assign it to an explicitly selected member, and verify local desired state while separating unverified provider synchronization.

  • Works in 12 steps: Call list_projects with limit: 100. This… → Call find_mcp for only that project with… → Call get_mcp_access for the selected… → …
  • Tasks that involve MCP servers
  • SKILL.md covers Safety rules and Workflow
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Manage MCP Access is an agent skill from speakeasy-api/gram. Create or select a narrow custom AICP MCP access role, assign it to an explicitly selected member, and verify local desired state while separating unverified provider synchronization.

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol. The repository describes itself as: Securely scale AI usage across your organization. A single stack to Connect, Secure, Observe and Distribute agents, MCPs, and Skills within your company. The licence is AGPL-3.0.

When your agent uses it

  • Tasks that involve MCP servers

Example prompts

  • “/manage-mcp-access”

Workflow steps

12 steps, taken from the first numbered list in SKILL.md.

  1. Call list_projects with limit: 100. This tool supports only limit (capped at 100), not cursor or search. If truncated: true, stop and hand…
  2. Call find_mcp for only that project with limit: 100. For an unfiltered list, follow next_cursor using cursor with the same project and no…
  3. Call get_mcp_access for the selected project and MCP. Explain its authorization mode, known tool catalogue, and current local role…
  4. Call list_access_roles. Present role names, types, privacy-safe member counts, and relevant MCP access summaries. Ask the user to choose…
  5. Resolve the custom role without silently broadening it
  6. After role creation, call both list_access_roles and get_mcp_access again. Continue only if the selected custom role exists, reports…
  7. Ask the user for an identity search of at least three characters, then call list_access_members without a role filter. Present only the…
  8. Immediately before assignment, refresh list_access_roles, get_mcp_access, and list_access_members for the exact prior choices. Keep the…
  9. Summarize the proposed local desired state using only the project name, MCP name, custom role name, masked member identity, and ALL…
  10. After confirmation, call assign_mcp_access_role using only the exact refreshed custom-role and member choices, the explicit project…
  11. The mutation response's snapshot_scope: assignment_commit identifies a historical snapshot of committed local desired state, including on…
  12. Report the selected project, MCP, custom role, masked member, and confirmed grants as committed local desired state only when supported by…

What it can do on your machine

Read from SKILL.md and the folder at commit 1378037. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Manage MCP Access loads about 2.4k tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 1,358 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from speakeasy-api/gram at commit 1378037, republished under its AGPL-3.0 licence (© speakeasy-api). 1,358 words, ~2,433 tokens.

Download SKILL.mdSave it as .claude/skills/manage-mcp-access/SKILL.md (or your agent's skills folder).
name
manage-mcp-access
description
Create or select a narrow custom AICP MCP access role, assign it to an explicitly selected member, and verify local desired state while separating unverified provider synchronization.

Manage MCP access

Use this workflow only through the authenticated Speakeasy AI Control Plane (AICP) Platform MCP. It mirrors the guarded dashboard workflow for giving one explicitly selected organization member access to one explicitly selected configured MCP through a custom role. Installing the package grants no organization or project access.

Safety rules

  • Never infer the project, MCP, custom role, member, or access rules from prior context. Present the eligible choices and require the user to select each target explicitly.
  • Show members only by the masked identities returned by list_access_members. Never reconstruct, request, or reveal an unmasked identity.
  • Do not expose raw identifiers or opaque references merely to distinguish choices. Present product names and masked identities; retain tool-returned selectors internally and use them only with the exact choice they represent.
  • Assign only a role whose returned type is custom and whose fresh get_mcp_access coverage reports assignment_eligible: true. Eligibility means the entire role contains only exact mcp:connect selectors for the selected project and MCP; non-MCP, broad, other-project, other-MCP, or unknown grants are not eligible.
  • Assigning a role includes all of its grants, not just the user's intended subset. Require explicit confirmation of ALL selected MCP grants by presenting EVERY assignment_rules entry from fresh get_mcp_access coverage. Each entry has all_tools and may have tool or disposition: all_tools: true means unrestricted tool access, including future tools, not merely the current catalogue. Explain each named tool and disposition rule, including future tools matching that disposition. Do not rely on allowed_known_tools to establish the full scope. Missing or incomplete assignment_rules is a stop condition, even when eligibility is true. Do not mutate or narrow a shared existing role to make it assignable; offer to create a dedicated narrow role instead.
  • Stop when member results are suppressed, ambiguous, expired, or do not contain the selected masked identity. Ask the user for a different identity query rather than guessing.
  • Stop if incomplete tool catalogue or unevaluated evidence prevents confirmation of exact scope. Never treat missing tools, tools_truncated: true, or unevaluated_grants: true as proof of narrow access.
  • Local role and membership reads describe local desired state only. Never claim provider synchronization has converged or that the member has effective provider access based on local reads, mutation success, or receipt replay.
  • If any read reports that the capability is unavailable, stop without claiming a change.

Workflow

  1. Call list_projects with limit: 100. This tool supports only limit (capped at 100), not cursor or search. If truncated: true, stop and hand off project selection to the AICP dashboard; do not invent pagination or treat the partial list as complete. Otherwise present eligible project names and ask the user to choose one exact project. Keep its returned selector internal.
  2. Call find_mcp for only that project with limit: 100. For an unfiltered list, follow next_cursor using cursor with the same project and no query until the list is complete. Cursor pagination is supported only for unfiltered results: never combine query and cursor. If a search result is truncated, narrow the query or switch to project-scoped unfiltered pagination. Stop if a complete, unambiguous choice cannot be established. Present configured MCP names and ask the user to choose one exact MCP. Keep its returned selector internal.
  3. Call get_mcp_access for the selected project and MCP. Explain its authorization mode, known tool catalogue, and current local role coverage. If it is not managed by role-based access, stop; this workflow must not imply that assigning a role will take effect. Check catalogue completeness and unevaluated evidence before proposing any mutation; if exact scope cannot be confirmed, stop and use the dashboard rather than guessing.
  4. Call list_access_roles. Present role names, types, privacy-safe member counts, and relevant MCP access summaries. Ask the user to choose an eligible existing custom role or explicitly choose to create a new custom role.
  5. Resolve the custom role without silently broadening it:
    • For a new role, collect its name, optional description, and exact MCP access rules from the selected MCP's current enumerable tools or supported disposition classes. Explain the full scope, including any disposition-based access to future tools. Show all proposed grants and ask for explicit confirmation, then call create_mcp_access_role for the exact project and rules.
    • For an existing custom role, compare its complete coverage from get_mcp_access with the user's requested outcome and require assignment_eligible: true. If it grants a broader outcome, is ineligible, or exact scope cannot be confirmed, do not assign it or call update_mcp_access_role to narrow or repurpose it. Offer to create a dedicated narrow role with a separately confirmed scope. Otherwise make no role mutation and explicitly confirm all grants, not merely the intended subset.
    • Use fresh tool-returned opaque references and any required freshness or retry fields only as agent-operational inputs. Do not describe those mechanics as part of the user-facing outcome.
  6. After role creation, call both list_access_roles and get_mcp_access again. Continue only if the selected custom role exists, reports assignment_eligible: true, and the re-read shows exactly all confirmed grants for the selected MCP. If the state conflicts or is incomplete, stop and report that no member assignment will be attempted.
  7. Ask the user for an identity search of at least three characters, then call list_access_members without a role filter. Present only the returned masked identities and current role names. Require the user to choose one exact masked member; do not accept an unmasked identity or select on their behalf.
  8. Immediately before assignment, refresh list_access_roles, get_mcp_access, and list_access_members for the exact prior choices. Keep the original identity query without a role filter so the privacy cohort is unchanged. Confirm internally that the project, MCP, custom role, all grants, assignment_eligible: true, and masked member still match. If a selector expired or the choices changed, present the safe names and masked identities again and ask the user to reselect. Stop on suppressed results or incomplete scope evidence.
  9. Summarize the proposed local desired state using only the project name, MCP name, custom role name, masked member identity, and ALL selected MCP grants. Present EVERY assignment_rules entry in product language for final confirmation, distinguishing unrestricted future-tool access from the known catalogue list. Explain that existing member roles are preserved and provider synchronization remains unverified. Ask for one final explicit confirmation of that complete assignment, not just the user's intended subset.
  10. After confirmation, call assign_mcp_access_role using only the exact refreshed custom-role and member choices, the explicit project, selected mcp_id, and confirmed: true. Pass the selected role's version from the immediately preceding get_mcp_access response as expected_role_version, and the selected member's version from the immediately preceding list_access_members response as expected_version. Supply a stable idempotency_key for retries of that exact request. Keep these fields internal. A version conflict requires fresh role and member reads, explicit reselection, and renewed confirmation before submitting a new request. Do not retry with another member, role, MCP, or project after a refusal or conflict.
  11. The mutation response's snapshot_scope: assignment_commit identifies a historical snapshot of committed local desired state, including on receipt replay. Never reuse its member version for a new write. Verify current local state rather than treating that snapshot as final proof:
    • Call list_access_roles again and confirm the selected role's current local state.
    • Call get_mcp_access again and confirm the role remains eligible and still has exactly all confirmed grants for the selected MCP.
    • Call list_access_members again with the original identity query without a role filter. Preserve the original privacy cohort; do not filter by the newly assigned role. Confirm the selected masked member is listed with that role when privacy-safe enumeration is available.
    • If member enumeration is suppressed or any evidence is stale, incomplete, or inconsistent, report local verification as incomplete. Never bypass suppression by changing filters or infer membership from counts.
  12. Report the selected project, MCP, custom role, masked member, and confirmed grants as committed local desired state only when supported by the evidence. Clearly separate the historical commit from current local verification and pending or unverified provider synchronization. These tools do not verify provider convergence or effective provider access; do not claim either from their local results.
Show full SKILL.md (21 more words)Show less

Project, MCP, custom-role, masked-member, complete-grant, and final assignment choices all remain explicit conversation checkpoints. All selectors and mutation-control fields remain agent-operational.

© speakeasy-api, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in server/internal/plugins/platform_mcp_skills/manage-mcp-access of speakeasy-api/gram.

Open the folder on GitHubat commit 1378037

Compare with similar skills

Manage MCP Access next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Manage MCP Access compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Manage MCP Access this skillspeakeasy-api/gram273—~2.4kAutomated safety check: PassAGPL-3.0
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official38k11 repos~3.1kAutomated safety check: PassApache-2.0
Crush Configurationcharmbracelet/crush29k—~3.7kAutomated safety check: PassCustom licence
Context Mode Output Sandboxmksglu/context-mode26k—~4.1kAutomated safety check: PassCustom licence

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed
  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Context Mode Output Sandbox

    mksglu/context-mode

    Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.

    26k GitHub stars~4.1k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Migrates the compatible subset of settings and global file-based MCP servers from the Warp desktop app into Warp Agent CLI without exposing credentials or state.

    65k GitHub starsUsed in 1 repo~2.1k tokens
    Agent WorkflowsAuto-check passed

More from speakeasy-api/gram

All 39 skills in this repo
  • Gram Playwright CLI

    speakeasy-api/gram

    A skill your agent uses when automating the Speakeasy dashboard in a browser, capturing screenshots, inspecting pages.

    273 GitHub stars~3.4k tokensUpdated today
    Auto-check passed
  • Transactional Email

    speakeasy-api/gram

    A skill your agent uses when adding, changing, restyling, reviewing, validating, or previewing a Speakeasy transactional email, in Go or in LMX/MJML — a template<name.go, a TemplateKey constant, a…

    273 GitHub stars~4.7k tokensUpdated today
    Auto-check passed
  • Admin Shadcn

    speakeasy-api/gram

    A skill your agent uses when adding, changing, or styling UI in client/admin (the Speakeasy admin dashboard) that touches shadcn/ui — a button, dialog, table, sidebar, badge, select, tabs, tooltip…

    273 GitHub stars~1k tokensUpdated today
    Auto-check passed
  • A skill your agent uses when adding, editing, reviewing, testing, or locating a reviewed skill distributed with the Platform MCP plugin; triggers include "Platform MCP skill", "platformmcpskills"…

    273 GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • Clickhouse

    speakeasy-api/gram

    A skill your agent uses when changing or reviewing Speakeasy ClickHouse schemas, migrations, queries, inserts, access principals, bootstrap SQL, Cloud compatibility, partial migration failures, or…

    273 GitHub stars~3.2k tokensUpdated today
    Auto-check passed
  • Feature Flag

    speakeasy-api/gram

    A skill your agent uses when gating a feature behind a flag, dogfooding or gradually rolling out a change, choosing between productfeatures and PostHog feature flags, adding or checking a product…

    273 GitHub stars~2.6k tokensUpdated today
    Auto-check passed

Categories

Questions about Manage MCP Access

What does Manage MCP Access do?

Create or select a narrow custom AICP MCP access role, assign it to an explicitly selected member, and verify local desired state while separating unverified provider synchronization. Manage MCP Access is an agent skill from speakeasy-api/gram. Create or select a narrow custom AICP MCP access role, assign it to an explicitly selected member, and verify local desired state while separating unverified provider synchronization.

When should I use Manage MCP Access?

Manage MCP Access fits situations like: tasks that involve MCP servers.

How do I install Manage MCP Access in Claude Code?

Run `npx skills add speakeasy-api/gram --skill manage-mcp-access -a claude-code`. Or copy the skill folder (server/internal/plugins/platform_mcp_skills/manage-mcp-access in speakeasy-api/gram) into .claude/skills/manage-mcp-access in your project. Claude Code loads it when a task matches its description.

How do I install Manage MCP Access in Codex?

Run `npx skills add speakeasy-api/gram --skill manage-mcp-access -a codex`. Or copy the skill folder (server/internal/plugins/platform_mcp_skills/manage-mcp-access in speakeasy-api/gram) into .agents/skills/manage-mcp-access in your project. Codex loads it when a task matches its description.

Can I use Manage MCP Access in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add speakeasy-api/gram --skill manage-mcp-access -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/manage-mcp-access, .gemini/skills/manage-mcp-access, .github/skills/manage-mcp-access and .opencode/skills/manage-mcp-access in your project.

What does Manage MCP Access need to run?

SKILL.md names no scripts, command-line tools or credentials: Manage MCP Access is instructions for the agent only.

Does Manage MCP Access access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Manage MCP Access safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Manage MCP Access use?

Manage MCP Access is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Manage MCP Access use?

About 2.4k tokens (SKILL.md is roughly 9.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Manage MCP Access?

Skills that share tags, products or a category with Manage MCP Access: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Crush Configuration (charmbracelet/crush, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Manage MCP Access?

speakeasy-api (a GitHub organization) maintains it in speakeasy-api/gram, which has 273 GitHub stars. The repository holds 39 skills in this directory. The repository was last updated on October 9, 2026.

Source: speakeasy-api/gram on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.