Skip to content

Commit d37097f

Browse files
SamMorrowDrumsCopilotolaservo
authored
docs(community): add Primitive Grouping Interest Group charter (#2942)
* docs(community): add Primitive Grouping Interest Group charter Port the charter for the Primitive Grouping Interest Group from the experimental-ext-grouping incubation repo into the canonical Interest Group Charters section, and register it in docs.json navigation. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * docs(community): sync Primitive Grouping charter with group repo PR #6 Port the updated charter from modelcontextprotocol/experimental-ext-grouping#6: add the #primitive-grouping-ig Discord channel, the within/beyond-scope problem statement, and the Goals, Organization Strategies, and IG Principles sections. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Co-authored-by: Ola Hungerford <olahungerford@gmail.com>
1 parent 2ffc3fa commit d37097f

2 files changed

Lines changed: 131 additions & 0 deletions

File tree

‎docs/community/interest-groups/primitive-grouping.mdx‎

Lines changed: 130 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,130 @@
1+
---
2+
title: Primitive Grouping Charter
3+
description: Charter for the MCP Primitive Grouping Interest Group.
4+
---
5+
6+
## Group Type
7+
8+
**Interest Group**
9+
10+
## Mission Statement
11+
12+
The Primitive Grouping Interest Group explores how MCP Primitives (Tools, Resources, Prompts, Tasks) might be organized, beyond the flat lists maintained by the protocol, and how such organization might benefit both MCP servers and clients. The group documents diverse requirements from clients, servers, and gateways, supports reference extensions of varied organization strategies, and feeds recommendations into the [SEP process](/community/sep-guidelines) rather than picking a single canonical pattern early.
13+
14+
## Scope
15+
16+
### In Scope
17+
18+
- **Requirements gathering**: documenting use cases and constraints
19+
- **Pattern exploration**: testing and evaluating various approaches
20+
- **Proof of concepts**: maintaining a shared repository of reference implementations and experimental findings
21+
22+
### Out of Scope
23+
24+
- **Approving spec changes**: this IG does not have authority to approve protocol changes; recommendations flow through the SEP process
25+
- **Implementation mandates**: the group can document patterns but cannot require specific client or server behavior
26+
27+
### Related Groups
28+
29+
- **[Tool Annotations IG](/community/interest-groups/tool-annotations)** - annotation-based filtering and selection of primitives intersects with how primitives are organized and surfaced
30+
- **[Skills Over MCP WG](/community/working-groups/skills-over-mcp)** - the MCP-and-Skills effort is evaluating how capabilities are discovered and organized, which overlaps with grouping
31+
- **[Registry WG](/community/working-groups/registry)** - organizing MCP servers (beyond this group's mandate) is evaluated here
32+
- **[Security IG](/community/interest-groups/security)** - organizing and disclosing primitives by privilege level is a security concern outside this group's scope
33+
34+
## Problem Statement
35+
36+
Flat lists of MCP primitives can be long and cumbersome to work with for several reasons. Many such problems are within the scope of this group, but some are not.
37+
38+
**Within Scope**
39+
40+
- **Context overload** - when loaded into the context of an LLM, a primitive list can overwhelm the model and lead to confusion and poor selection
41+
- **Inefficient operations** - long lists in the context consume many tokens, which increases processing cost and response latency
42+
- **Poor developer experience** - the lack of organizational tools for primitives makes them harder to manage and maintain
43+
44+
**Beyond Scope**
45+
46+
- **Organization for security** - organizing and disclosing primitives to clients based on their privilege level is an important problem but beyond this group's mandate
47+
- **Organizing MCP servers** - the MCP Registry and MCP-and-Skills groups are evaluating how different servers should be organized to improve the client experience
48+
49+
## Goals
50+
51+
1. **Documenting requirements and experiences** - document diverse requirements for the different clients, servers, and gateways that implement these extensions. We will **not** try to find consensus early on, but aim to document the trade-offs based on feedback from real-world experience.
52+
2. **Reference extensions** - many possible organization mechanisms are emerging, and it may be too early to select one canonical pattern. Different servers are implementing similar features, but the lack of standardization limits clients' ability to leverage them effectively. This group will support reference extensions of varied organization strategies, e.g., grouping, tool-search, code-mode.
53+
3. **Evangelizing standards** - invite feedback from developers and maintainers of large MCP servers and clients to migrate away from bespoke implementations toward standardized extensions.
54+
55+
## Organization Strategies
56+
57+
See [Approaches](https://github.com/modelcontextprotocol/experimental-ext-grouping/blob/main/docs/approaches.md) for detailed descriptions of each strategy, including prior art, examples, and discussion links.
58+
59+
## IG Principles
60+
61+
1. **Document discussions** - the IG aims to document the trade-offs and discussions rather than dictate one specific implementation. Prefer GitHub Discussions on the IG repository over prolonged Discord threads. Meeting notes from synchronous IG calls are also uploaded to GitHub Discussions for future reference.
62+
2. **Experimental extensions** - the repository houses experimental extensions for different approaches. Extensions SHOULD support at least Python and TypeScript implementations and include (1) end-to-end working demonstrations and (2) detailed instructions for how others can integrate with them.
63+
3. **Feedback from deployments** - the IG solicits deployment experiences and feedback from users of extensions to prioritize feature development and changes.
64+
65+
## Leadership
66+
67+
| Role | Name | Organization | GitHub | Term |
68+
| ----------- | ----------- | ------------------------ | ---------------------------------------------------- | ------- |
69+
| Facilitator | Tapan Chugh | University of Washington | [@chughtapan](https://github.com/chughtapan) | Initial |
70+
| Facilitator | Sam Morrow | GitHub | [@SamMorrowDrums](https://github.com/SamMorrowDrums) | Initial |
71+
72+
## Membership
73+
74+
| Name | Organization | GitHub | Discord | Level |
75+
| ----------- | ------------------------ | ---------------------------------------------------- | ------- | ----------- |
76+
| Tapan Chugh | University of Washington | [@chughtapan](https://github.com/chughtapan) | | Facilitator |
77+
| Sam Morrow | GitHub | [@SamMorrowDrums](https://github.com/SamMorrowDrums) | | Facilitator |
78+
| Cliff Hall | Futurescale | [@cliffhall](https://github.com/cliffhall) | | Maintainer |
79+
80+
## Operations
81+
82+
| Meeting | Frequency | Duration | Purpose |
83+
| ---------- | --------- | -------- | -------------------------------------------------------------- |
84+
| Discussion | TBD | TBD | Requirements alignment, approach review, experimental findings |
85+
86+
Open to anyone. Join the [#primitive-grouping-ig](https://discord.com/channels/1358869848138059966/1425903819186770064) channel on the [MCP Contributors Discord](/community/communication#discord).
87+
88+
## Discussion Topics
89+
90+
The following items form the IG's current work agenda. This list is not exhaustive and will evolve as the group identifies new areas of interest.
91+
92+
| Item | Status | Champion | Notes |
93+
| ---------------------------------- | ----------- | ---------------- | ----------------------------------------------------------------- |
94+
| Requirements alignment | In Progress | All facilitators | Review approaches, identify common requirements and gaps |
95+
| Experimental findings repo section | Proposed | TBD | Dedicated repo section for implementations and evaluation results |
96+
| MCP Grouping Convention v0.1 | Proposed | TBD | Documented pattern (not spec) for grouping of primitives |
97+
98+
## Lifecycle
99+
100+
**Current Status: Active Exploration**
101+
102+
### Graduation Criteria (IG → WG)
103+
104+
This IG may propose becoming a Working Group if:
105+
106+
- Clear consensus emerges on an approach requiring sustained spec work
107+
- Cross-cutting coordination requires formal authority delegation
108+
- At least two Core Maintainers sponsor WG formation
109+
110+
### Retirement Criteria
111+
112+
- Problem space resolved (conventions established, absorbed into other WGs)
113+
- Insufficient participation to maintain momentum
114+
- Community consensus that grouping doesn't belong in MCP protocol scope
115+
116+
## Success Criteria
117+
118+
- **Short-term**: documented consensus on requirements and evaluation of existing approaches
119+
- **Medium-term**: clear recommendation (convention vs. protocol extension vs. both)
120+
- **Long-term**: interoperable grouping convention across MCP servers and clients
121+
122+
## Resources
123+
124+
- [Experimental repo](https://github.com/modelcontextprotocol/experimental-ext-grouping) - incubation space for the Primitive Grouping Interest Group
125+
126+
## Changelog
127+
128+
| Date | Change |
129+
| ---------- | --------------- |
130+
| 2026-06-18 | Initial charter |

‎docs/docs.json‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -508,6 +508,7 @@
508508
"pages": [
509509
"community/interest-groups/auth",
510510
"community/interest-groups/enterprise-managed-authorization",
511+
"community/interest-groups/primitive-grouping",
511512
"community/interest-groups/security",
512513
"community/interest-groups/tool-annotations"
513514
]

0 commit comments

Comments
 (0)